# Agent Skill Package: phishing

You are loading a published Agent Skill. Follow SKILL.md exactly.
Supporting files from the original zip are inlined below.
When SKILL.md says to read `references/...` or `scripts/...`, use the matching FILE section here — do not say the file is missing.

Canonical URL: https://skill.hk/s/phishing.md
Human page: https://skill.hk/s/phishing

Files (4):
- SKILL.md
- LICENSE
- references/api-reference.md
- scripts/agent.py

========================================================================
FILE: SKILL.md
========================================================================

---
name: analyzing-certificate-transparency-for-phishing
description: Monitor Certificate Transparency logs using crt.sh and Certstream to
  detect phishing domains, lookalike certificates, and unauthorized certificate issuance
  targeting your organization.
domain: cybersecurity
subdomain: threat-intelligence
tags:
- certificate-transparency
- ct-logs
- phishing
- crt-sh
- certstream
- ssl
- domain-monitoring
- threat-intelligence
version: '1.0'
author: mahipal
license: Apache-2.0
atlas_techniques:
- AML.T0052
nist_csf:
- ID.RA-01
- ID.RA-05
- DE.CM-01
- DE.AE-02
mitre_attack:
- T1583.001
- T1583.004
- T1566.002
- T1608.005
- T1596.003
mitre_f3:
  version: '1.1'
  tactics:
  - resource-development
  - reconnaissance
  - initial-access
  techniques:
  - id: T1583.001
    name: 'Acquire Infrastructure: Domains'
    tactic: resource-development
    source: attack
  - id: F1020.002
    name: 'Create Fake Materials: Fake Website'
    tactic: resource-development
    source: f3
  - id: T1593
    name: Search Open Websites/Domains
    tactic: reconnaissance
    source: attack
  - id: T1598
    name: Phishing for Information
    tactic: reconnaissance
    source: attack
  - id: T1660
    name: Phishing
    tactic: initial-access
    source: attack
---
# Analyzing Certificate Transparency for Phishing

## Overview

Certificate Transparency (CT) is an Internet security standard that creates a public, append-only log of all issued SSL/TLS certificates. Monitoring CT logs enables early detection of phishing domains that register certificates mimicking legitimate brands, unauthorized certificate issuance for owned domains, and certificate-based attack infrastructure. This skill covers querying CT logs via crt.sh, real-time monitoring with Certstream, building automated alerting for suspicious certificates, and integrating findings into threat intelligence workflows.


## When to Use

- When investigating security incidents that require analyzing certificate transparency for phishing
- When building detection rules or threat hunting queries for this domain
- When SOC analysts need structured procedures for this analysis type
- When validating security monitoring coverage for related attack techniques

## Prerequisites

- Python 3.9+ with `requests`, `certstream`, `tldextract`, `Levenshtein` libraries
- Access to crt.sh (https://crt.sh/) for historical CT log queries
- Certstream (https://certstream.calidog.io/) for real-time monitoring
- List of organization domains and brand keywords to monitor
- Understanding of SSL/TLS certificate structure and issuance process

## Key Concepts

### Certificate Transparency Logs

CT logs are cryptographically assured, publicly auditable, append-only records of TLS certificate issuance. Major CAs (Let's Encrypt, DigiCert, Sectigo, Google Trust Services) submit all issued certificates to multiple CT logs. As of 2025, Chrome and Safari require CT for all publicly trusted certificates.

### Phishing Detection via CT

Attackers register lookalike domains and obtain free certificates (often from Let's Encrypt) to make phishing sites appear legitimate with HTTPS. CT monitoring detects these early because the certificate appears in logs before the phishing campaign launches, providing a window for proactive blocking.

### crt.sh Database

crt.sh is a free web interface and PostgreSQL database operated by Sectigo that indexes CT logs. It supports wildcard searches (`%.example.com`), direct SQL queries, and JSON API responses. It tracks certificate issuance, expiration, and revocation across all major CT logs.

## Workflow

### Step 1: Query crt.sh for Certificate History

```python
import requests
import json
from datetime import datetime
import tldextract

class CTLogMonitor:
    CRT_SH_URL = "https://crt.sh"

    def __init__(self, monitored_domains, brand_keywords):
        self.monitored_domains = monitored_domains
        self.brand_keywords = [k.lower() for k in brand_keywords]

    def query_crt_sh(self, domain, include_expired=False):
        """Query crt.sh for certificates matching a domain."""
        params = {
            "q": f"%.{domain}",
            "output": "json",
        }
        if not include_expired:
            params["exclude"] = "expired"

        resp = requests.get(self.CRT_SH_URL, params=params, timeout=30)
        if resp.status_code == 200:
            certs = resp.json()
            print(f"[+] crt.sh: {len(certs)} certificates for *.{domain}")
            return certs
        return []

    def find_suspicious_certs(self, domain):
        """Find certificates that may be phishing attempts."""
        certs = self.query_crt_sh(domain)
        suspicious = []

        for cert in certs:
            common_name = cert.get("common_name", "").lower()
            name_value = cert.get("name_value", "").lower()
            issuer = cert.get("issuer_name", "")
            not_before = cert.get("not_before", "")
            not_after = cert.get("not_after", "")

            # Check for exact domain matches (legitimate)
            extracted = tldextract.extract(common_name)
            cert_domain = f"{extracted.domain}.{extracted.suffix}"
            if cert_domain == domain:
                continue  # Legitimate certificate

            # Flag suspicious patterns
            flags = []
            if domain.replace(".", "") in common_name.replace(".", ""):
                flags.append("contains target domain string")
            if any(kw in common_name for kw in self.brand_keywords):
                flags.append("contains brand keyword")
            if "let's encrypt" in issuer.lower():
                flags.append("free CA (Let's Encrypt)")

            if flags:
                suspicious.append({
                    "common_name": cert.get("common_name", ""),
                    "name_value": cert.get("name_value", ""),
                    "issuer": issuer,
                    "not_before": not_before,
                    "not_after": not_after,
                    "serial": cert.get("serial_number", ""),
                    "flags": flags,
                    "crt_sh_id": cert.get("id", ""),
                    "crt_sh_url": f"https://crt.sh/?id={cert.get('id', '')}",
                })

        print(f"[+] Found {len(suspicious)} suspicious certificates")
        return suspicious

monitor = CTLogMonitor(
    monitored_domains=["mycompany.com", "mycompany.org"],
    brand_keywords=["mycompany", "mybrand", "myproduct"],
)
suspicious = monitor.find_suspicious_certs("mycompany.com")
for cert in suspicious[:5]:
    print(f"  [{cert['common_name']}] Flags: {cert['flags']}")
```

### Step 2: Real-Time Monitoring with Certstream

```python
import certstream
import Levenshtein
import re
from datetime import datetime

class CertstreamMonitor:
    def __init__(self, watched_domains, brand_keywords, similarity_threshold=0.8):
        self.watched_domains = [d.lower() for d in watched_domains]
        self.brand_keywords = [k.lower() for k in brand_keywords]
        self.threshold = similarity_threshold
        self.alerts = []

    def start_monitoring(self, max_alerts=100):
        """Start real-time CT log monitoring."""
        print("[*] Starting Certstream monitoring...")
        print(f"    Watching: {self.watched_domains}")
        print(f"    Keywords: {self.brand_keywords}")

        def callback(message, context):
            if message["message_type"] == "certificate_update":
                data = message["data"]
                leaf = data.get("leaf_cert", {})
                all_domains = leaf.get("all_domains", [])

                for domain in all_domains:
                    domain_lower = domain.lower().strip("*.")
                    if self._is_suspicious(domain_lower):
                        alert = {
                            "domain": domain,
                            "all_domains": all_domains,
                            "issuer": leaf.get("issuer", {}).get("O", ""),
                            "fingerprint": leaf.get("fingerprint", ""),
                            "not_before": leaf.get("not_before", ""),
                            "detected_at": datetime.now().isoformat(),
                            "reason": self._get_reason(domain_lower),
                        }
                        self.alerts.append(alert)
                        print(f"  [ALERT] {domain} - {alert['reason']}")

                        if len(self.alerts) >= max_alerts:
                            raise KeyboardInterrupt

        try:
            certstream.listen_for_events(callback, url="wss://certstream.calidog.io/")
        except KeyboardInterrupt:
            print(f"\n[+] Monitoring stopped. {len(self.alerts)} alerts collected.")
        return self.alerts

    def _is_suspicious(self, domain):
        """Check if domain is suspicious relative to watched domains."""
        for watched in self.watched_domains:
            # Exact keyword match
            watched_base = watched.split(".")[0]
            if watched_base in domain and domain != watched:
                return True

            # Levenshtein distance (typosquatting detection)
            domain_base = tldextract.extract(domain).domain
            similarity = Levenshtein.ratio(watched_base, domain_base)
            if similarity >= self.threshold and domain_base != watched_base:
                return True

        # Brand keyword match
        for keyword in self.brand_keywords:
            if keyword in domain:
                return True

        return False

    def _get_reason(self, domain):
        """Determine why domain was flagged."""
        reasons = []
        for watched in self.watched_domains:
            watched_base = watched.split(".")[0]
            if watched_base in domain:
                reasons.append(f"contains '{watched_base}'")
            domain_base = tldextract.extract(domain).domain
            similarity = Levenshtein.ratio(watched_base, domain_base)
            if similarity >= self.threshold and domain_base != watched_base:
                reasons.append(f"similar to '{watched}' ({similarity:.0%})")
        for kw in self.brand_keywords:
            if kw in domain:
                reasons.append(f"brand keyword '{kw}'")
        return "; ".join(reasons) if reasons else "unknown"

cs_monitor = CertstreamMonitor(
    watched_domains=["mycompany.com"],
    brand_keywords=["mycompany", "mybrand"],
    similarity_threshold=0.75,
)
alerts = cs_monitor.start_monitoring(max_alerts=50)
```

### Step 3: Enumerate Subdomains from CT Logs

```python
def enumerate_subdomains_ct(domain):
    """Discover all subdomains from Certificate Transparency logs."""
    params = {"q": f"%.{domain}", "output": "json"}
    resp = requests.get("https://crt.sh", params=params, timeout=30)

    if resp.status_code != 200:
        return []

    certs = resp.json()
    subdomains = set()
    for cert in certs:
        name_value = cert.get("name_value", "")
        for name in name_value.split("\n"):
            name = name.strip().lower()
            if name.endswith(f".{domain}") or name == domain:
                name = name.lstrip("*.")
                subdomains.add(name)

    sorted_subs = sorted(subdomains)
    print(f"[+] CT subdomain enumeration for {domain}: {len(sorted_subs)} subdomains")
    return sorted_subs

subdomains = enumerate_subdomains_ct("example.com")
for sub in subdomains[:20]:
    print(f"  {sub}")
```

### Step 4: Generate CT Intelligence Report

```python
def generate_ct_report(suspicious_certs, certstream_alerts, domain):
    report = f"""# Certificate Transparency Intelligence Report
## Target Domain: {domain}
## Generated: {datetime.now().isoformat()}

## Summary
- Suspicious certificates found: {len(suspicious_certs)}
- Real-time alerts triggered: {len(certstream_alerts)}

## Suspicious Certificates (crt.sh)
| Common Name | Issuer | Flags | crt.sh Link |
|------------|--------|-------|-------------|
"""
    for cert in suspicious_certs[:20]:
        flags = "; ".join(cert.get("flags", []))
        report += (f"| {cert['common_name']} | {cert['issuer'][:30]} "
                   f"| {flags} | [View]({cert['crt_sh_url']}) |\n")

    report += f"""
## Real-Time Certstream Alerts
| Domain | Issuer | Reason | Detected |
|--------|--------|--------|----------|
"""
    for alert in certstream_alerts[:20]:
        report += (f"| {alert['domain']} | {alert['issuer']} "
                   f"| {alert['reason']} | {alert['detected_at'][:19]} |\n")

    report += """
## Recommendations
1. Add flagged domains to DNS sinkhole / web proxy blocklist
2. Submit takedown requests for confirmed phishing domains
3. Monitor CT logs continuously for new certificate registrations
4. Implement CAA DNS records to restrict certificate issuance for your domains
5. Deploy DMARC to prevent email spoofing from lookalike domains
"""
    with open(f"ct_report_{domain.replace('.','_')}.md", "w") as f:
        f.write(report)
    print(f"[+] CT report saved")
    return report

generate_ct_report(suspicious, alerts if 'alerts' in dir() else [], "mycompany.com")
```

## Validation Criteria

- crt.sh queries return certificate data for target domains
- Suspicious certificates identified based on lookalike patterns
- Certstream real-time monitoring detects new phishing certificates
- Subdomain enumeration produces comprehensive list from CT logs
- Alerts generated with reason classification
- CT intelligence report created with actionable recommendations

## References

- [crt.sh Certificate Search](https://crt.sh/)
- [Certstream Real-Time CT Monitor](https://certstream.calidog.io/)
- [River Security: CT Logs for Attack Surface Discovery](https://riversecurity.eu/finding-attack-surface-and-fraudulent-domains-via-certificate-transparency-logs/)
- [Let's Encrypt: Certificate Transparency Logs](https://letsencrypt.org/docs/ct-logs/)
- [SSLMate Cert Spotter](https://sslmate.com/certspotter/)
- [CyberSierra: CT Logs as Early Warning System](https://cybersierra.co/blog/ssl-certificate-transparency-logs/)


========================================================================
FILE: LICENSE
========================================================================


                                 Apache License
                           Version 2.0, January 2004
                        http://www.apache.org/licenses/

   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION

   1. Definitions.

      "License" shall mean the terms and conditions for use, reproduction,
      and distribution as defined by Sections 1 through 9 of this document.

      "Licensor" shall mean the copyright owner or entity authorized by
      the copyright owner that is granting the License.

      "Legal Entity" shall mean the union of the acting entity and all
      other entities that control, are controlled by, or are under common
      control with that entity. For the purposes of this definition,
      "control" means (i) the power, direct or indirect, to cause the
      direction or management of such entity, whether by contract or
      otherwise, or (ii) ownership of fifty percent (50%) or more of the
      outstanding shares, or (iii) beneficial ownership of such entity.

      "You" (or "Your") shall mean an individual or Legal Entity
      exercising permissions granted by this License.

      "Source" form shall mean the preferred form for making modifications,
      including but not limited to software source code, documentation
      source, and configuration files.

      "Object" form shall mean any form resulting from mechanical
      transformation or translation of a Source form, including but
      not limited to compiled object code, generated documentation,
      and conversions to other media types.

      "Work" shall mean the work of authorship, whether in Source or
      Object form, made available under the License, as indicated by a
      copyright notice that is included in or attached to the work
      (an example is provided in the Appendix below).

      "Derivative Works" shall mean any work, whether in Source or Object
      form, that is based on (or derived from) the Work and for which the
      editorial revisions, annotations, elaborations, or other modifications
      represent, as a whole, an original work of authorship. For the purposes
      of this License, Derivative Works shall not include works that remain
      separable from, or merely link (or bind by name) to the interfaces of,
      the Work and Derivative Works thereof.

      "Contribution" shall mean any work of authorship, including
      the original version of the Work and any modifications or additions
      to that Work or Derivative Works thereof, that is intentionally
      submitted to the Licensor for inclusion in the Work by the copyright owner
      or by an individual or Legal Entity authorized to submit on behalf of
      the copyright owner. For the purposes of this definition, "submitted"
      means any form of electronic, verbal, or written communication sent
      to the Licensor or its representatives, including but not limited to
      communication on electronic mailing lists, source code control systems,
      and issue tracking systems that are managed by, or on behalf of, the
      Licensor for the purpose of discussing and improving the Work, but
      excluding communication that is conspicuously marked or otherwise
      designated in writing by the copyright owner as "Not a Contribution."

      "Contributor" shall mean Licensor and any individual or Legal Entity
      on behalf of whom a Contribution has been received by the Licensor and
      subsequently incorporated within the Work.

   2. Grant of Copyright License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      copyright license to reproduce, prepare Derivative Works of,
      publicly display, publicly perform, sublicense, and distribute the
      Work and such Derivative Works in Source or Object form.

   3. Grant of Patent License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      (except as stated in this section) patent license to make, have made,
      use, offer to sell, sell, import, and otherwise transfer the Work,
      where such license applies only to those patent claims licensable
      by such Contributor that are necessarily infringed by their
      Contribution(s) alone or by combination of their Contribution(s)
      with the Work to which such Contribution(s) was submitted. If You
      institute patent litigation against any entity (including a
      cross-claim or counterclaim in a lawsuit) alleging that the Work
      or a Contribution incorporated within the Work constitutes direct
      or contributory patent infringement, then any patent licenses
      granted to You under this License for that Work shall terminate
      as of the date such litigation is filed.

   4. Redistribution. You may reproduce and distribute copies of the
      Work or Derivative Works thereof in any medium, with or without
      modifications, and in Source or Object form, provided that You
      meet the following conditions:

      (a) You must give any other recipients of the Work or
          Derivative Works a copy of this License; and

      (b) You must cause any modified files to carry prominent notices
          stating that You changed the files; and

      (c) You must retain, in the Source form of any Derivative Works
          that You distribute, all copyright, patent, trademark, and
          attribution notices from the Source form of the Work,
          excluding those notices that do not pertain to any part of
          the Derivative Works; and

      (d) If the Work includes a "NOTICE" text file as part of its
          distribution, then any Derivative Works that You distribute must
          include a readable copy of the attribution notices contained
          within such NOTICE file, excluding any notices that do not
          pertain to any part of the Derivative Works, in at least one
          of the following places: within a NOTICE text file distributed
          as part of the Derivative Works; within the Source form or
          documentation, if provided along with the Derivative Works; or,
          within a display generated by the Derivative Works, if and
          wherever such third-party notices normally appear. The contents
          of the NOTICE file are for informational purposes only and
          do not modify the License. You may add Your own attribution
          notices within Derivative Works that You distribute, alongside
          or as an addendum to the NOTICE text from the Work, provided
          that such additional attribution notices cannot be construed
          as modifying the License.

      You may add Your own copyright statement to Your modifications and
      may provide additional or different license terms and conditions
      for use, reproduction, or distribution of Your modifications, or
      for any such Derivative Works as a whole, provided Your use,
      reproduction, and distribution of the Work otherwise complies with
      the conditions stated in this License.

   5. Submission of Contributions. Unless You explicitly state otherwise,
      any Contribution intentionally submitted for inclusion in the Work
      by You to the Licensor shall be under the terms and conditions of
      this License, without any additional terms or conditions.
      Notwithstanding the above, nothing herein shall supersede or modify
      the terms of any separate license agreement you may have executed
      with Licensor regarding such Contributions.

   6. Trademarks. This License does not grant permission to use the trade
      names, trademarks, service marks, or product names of the Licensor,
      except as required for reasonable and customary use in describing the
      origin of the Work and reproducing the content of the NOTICE file.

   7. Disclaimer of Warranty. Unless required by applicable law or
      agreed to in writing, Licensor provides the Work (and each
      Contributor provides its Contributions) on an "AS IS" BASIS,
      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
      implied, including, without limitation, any warranties or conditions
      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
      PARTICULAR PURPOSE. You are solely responsible for determining the
      appropriateness of using or redistributing the Work and assume any
      risks associated with Your exercise of permissions under this License.

   8. Limitation of Liability. In no event and under no legal theory,
      whether in tort (including negligence), contract, or otherwise,
      unless required by applicable law (such as deliberate and grossly
      negligent acts) or agreed to in writing, shall any Contributor be
      liable to You for damages, including any direct, indirect, special,
      incidental, or consequential damages of any character arising as a
      result of this License or out of the use or inability to use the
      Work (including but not limited to damages for loss of goodwill,
      work stoppage, computer failure or malfunction, or any and all
      other commercial damages or losses), even if such Contributor
      has been advised of the possibility of such damages.

   9. Accepting Warranty or Additional Liability. While redistributing
      the Work or Derivative Works thereof, You may choose to offer,
      and charge a fee for, acceptance of support, warranty, indemnity,
      or other liability obligations and/or rights consistent with this
      License. However, in accepting such obligations, You may act only
      on Your own behalf and on Your sole responsibility, not on behalf
      of any other Contributor, and only if You agree to indemnify,
      defend, and hold each Contributor harmless for any liability
      incurred by, or claims asserted against, such Contributor by reason
      of your accepting any such warranty or additional liability.

   END OF TERMS AND CONDITIONS

   APPENDIX: How to apply the Apache License to your work.

      To apply the Apache License to your work, attach the following
      boilerplate notice, with the fields enclosed by brackets "[]"
      replaced with your own identifying information. (Don't include
      the brackets!)  The text should be enclosed in the appropriate
      comment syntax for the file format. Please do not remove or change
      the license header comment from a contributed file except when
      necessary.

   Copyright 2026 mukul975

   Licensed under the Apache License, Version 2.0 (the "License");
   you may not use this file except in compliance with the License.
   You may obtain a copy of the License at

       http://www.apache.org/licenses/LICENSE-2.0

   Unless required by applicable law or agreed to in writing, software
   distributed under the License is distributed on an "AS IS" BASIS,
   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   See the License for the specific language governing permissions and
   limitations under the License.


========================================================================
FILE: references/api-reference.md
========================================================================

# API Reference: Certificate Transparency Phishing Detection

## crt.sh API

### Search Certificates
```bash
# JSON output
curl "https://crt.sh/?q=%.example.com&output=json"

# Exclude expired
curl "https://crt.sh/?q=%.example.com&output=json&exclude=expired"

# Exact match
curl "https://crt.sh/?q=example.com&output=json"
```

### Response Fields
| Field | Description |
|-------|-------------|
| `id` | Certificate ID in crt.sh database |
| `common_name` | Certificate CN |
| `name_value` | All SANs (newline-separated) |
| `issuer_name` | Certificate Authority |
| `not_before` | Validity start |
| `not_after` | Validity end |
| `serial_number` | Certificate serial |

## Certstream - Real-time CT Monitoring

### Python Client
```python
import certstream

def callback(message, context):
    if message["message_type"] == "certificate_update":
        data = message["data"]
        domains = data["leaf_cert"]["all_domains"]
        for domain in domains:
            if "example" in domain:
                print(f"[ALERT] {domain}")

certstream.listen_for_events(callback, url="wss://certstream.calidog.io/")
```

### Message Fields
| Field | Path |
|-------|------|
| Domains | `data.leaf_cert.all_domains` |
| Issuer | `data.leaf_cert.issuer.O` |
| Subject | `data.leaf_cert.subject.CN` |
| Fingerprint | `data.leaf_cert.fingerprint` |
| Source | `data.source.name` |

## CT Log Servers

| Log | Operator | URL |
|-----|----------|-----|
| Argon | Google | `ct.googleapis.com/logs/argon2024` |
| Xenon | Google | `ct.googleapis.com/logs/xenon2024` |
| Nimbus | Cloudflare | `ct.cloudflare.com/logs/nimbus2024` |
| Oak | Let's Encrypt | `oak.ct.letsencrypt.org/2024h1` |
| Yeti | DigiCert | `yeti2024.ct.digicert.com/log` |

## Phishing Detection Techniques

### Homoglyph / IDN Attacks
| Original | Lookalike | Technique |
|----------|-----------|-----------|
| example.com | examp1e.com | Character substitution (l→1) |
| google.com | gооgle.com | Cyrillic о (U+043E) |
| paypal.com | paypa1.com | l→1 substitution |
| microsoft.com | mіcrosoft.com | Cyrillic і (U+0456) |

### dnstwist Integration
```bash
dnstwist -r -f json example.com   # Generate and resolve permutations
dnstwist -w wordlist.txt example.com  # Dictionary-based
```

## Certificate Details Lookup
```bash
# Get full certificate from crt.sh
curl "https://crt.sh/?d=<cert_id>"

# OpenSSL inspection
openssl s_client -connect domain.com:443 -servername domain.com </dev/null 2>/dev/null | \
  openssl x509 -noout -text
```

## Suspicious Indicators
| Pattern | Risk Level |
|---------|-----------|
| Free CA + new domain + brand keyword | HIGH |
| Wildcard cert on recently registered domain | HIGH |
| Multiple certs for slight domain variants | MEDIUM |
| IDN/punycode domain mimicking brand | HIGH |
| Cert issued same day as domain registration | MEDIUM |


========================================================================
FILE: scripts/agent.py
========================================================================

#!/usr/bin/env python3
"""Certificate Transparency monitoring agent for phishing detection.

Queries crt.sh for certificates matching target domains, detects lookalike
certificates, and identifies potential phishing infrastructure.
"""

import json
import sys
from collections import defaultdict

try:
    import requests
    HAS_REQUESTS = True
except ImportError:
    HAS_REQUESTS = False


def query_crtsh(domain, wildcard=True, expired=False):
    """Query crt.sh for certificates matching a domain."""
    if not HAS_REQUESTS:
        return []
    query = f"%.{domain}" if wildcard else domain
    params = {"q": query, "output": "json"}
    if not expired:
        params["exclude"] = "expired"
    try:
        resp = requests.get("https://crt.sh/", params=params, timeout=30)
        resp.raise_for_status()
        return resp.json()
    except (requests.RequestException, json.JSONDecodeError) as e:
        return [{"error": str(e)}]


def find_lookalike_domains(target_domain, ct_results):
    """Identify certificates for domains that look similar to the target."""
    base = target_domain.split(".")[0].lower()
    lookalikes = []
    for cert in ct_results:
        cn = cert.get("common_name", "").lower()
        names = cert.get("name_value", "").lower().split("\n")
        for name in [cn] + names:
            name = name.strip()
            if not name or name == target_domain:
                continue
            similarity = calculate_similarity(base, name.split(".")[0])
            if similarity > 0.6 and name != target_domain:
                lookalikes.append({
                    "domain": name,
                    "similarity": round(similarity, 3),
                    "issuer": cert.get("issuer_name", ""),
                    "not_before": cert.get("not_before", ""),
                    "not_after": cert.get("not_after", ""),
                    "cert_id": cert.get("id"),
                })
    seen = set()
    unique = []
    for l in sorted(lookalikes, key=lambda x: -x["similarity"]):
        if l["domain"] not in seen:
            seen.add(l["domain"])
            unique.append(l)
    return unique


def calculate_similarity(s1, s2):
    """Calculate string similarity using Levenshtein-like ratio."""
    if s1 == s2:
        return 1.0
    len1, len2 = len(s1), len(s2)
    if len1 == 0 or len2 == 0:
        return 0.0
    matrix = [[0] * (len2 + 1) for _ in range(len1 + 1)]
    for i in range(len1 + 1):
        matrix[i][0] = i
    for j in range(len2 + 1):
        matrix[0][j] = j
    for i in range(1, len1 + 1):
        for j in range(1, len2 + 1):
            cost = 0 if s1[i-1] == s2[j-1] else 1
            matrix[i][j] = min(matrix[i-1][j] + 1, matrix[i][j-1] + 1,
                               matrix[i-1][j-1] + cost)
    distance = matrix[len1][len2]
    return 1.0 - distance / max(len1, len2)


HOMOGLYPH_MAP = {
    "a": ["а", "@", "4"], "e": ["е", "3"], "o": ["о", "0"],
    "i": ["і", "1", "l"], "l": ["1", "i", "I"],
    "s": ["5", "$"], "t": ["7"], "g": ["9", "q"],
}


def detect_homoglyph_domains(target_domain, ct_results):
    """Detect domains using homoglyph/IDN attacks against target."""
    findings = []
    base = target_domain.split(".")[0].lower()
    for cert in ct_results:
        names = cert.get("name_value", "").lower().split("\n")
        for name in names:
            name = name.strip()
            if not name or name == target_domain:
                continue
            name_base = name.split(".")[0]
            if len(name_base) == len(base):
                diffs = sum(1 for a, b in zip(base, name_base) if a != b)
                if 0 < diffs <= 2:
                    findings.append({
                        "domain": name,
                        "char_differences": diffs,
                        "cert_id": cert.get("id"),
                        "issuer": cert.get("issuer_name", ""),
                    })
    return findings


def analyze_issuer_patterns(ct_results):
    """Analyze certificate issuer patterns for anomalies."""
    issuer_counts = defaultdict(int)
    free_cas = ["Let's Encrypt", "ZeroSSL", "Buypass"]
    for cert in ct_results:
        issuer = cert.get("issuer_name", "Unknown")
        issuer_counts[issuer] += 1
    free_ca_certs = sum(
        count for issuer, count in issuer_counts.items()
        if any(ca.lower() in issuer.lower() for ca in free_cas)
    )
    return {
        "issuers": dict(issuer_counts),
        "total_certs": len(ct_results),
        "free_ca_count": free_ca_certs,
        "free_ca_ratio": round(free_ca_certs / max(len(ct_results), 1), 3),
    }


def detect_wildcard_abuse(ct_results):
    """Detect suspicious wildcard certificate patterns."""
    wildcards = []
    for cert in ct_results:
        cn = cert.get("common_name", "")
        if cn.startswith("*."):
            wildcards.append({
                "domain": cn,
                "issuer": cert.get("issuer_name", ""),
                "not_before": cert.get("not_before", ""),
            })
    return wildcards


def generate_report(target_domain, ct_results):
    """Generate comprehensive CT monitoring report."""
    lookalikes = find_lookalike_domains(target_domain, ct_results)
    homoglyphs = detect_homoglyph_domains(target_domain, ct_results)
    issuer_analysis = analyze_issuer_patterns(ct_results)
    wildcards = detect_wildcard_abuse(ct_results)

    risk_score = 0
    risk_score += min(len(lookalikes) * 10, 40)
    risk_score += min(len(homoglyphs) * 15, 30)
    risk_score += 20 if issuer_analysis["free_ca_ratio"] > 0.8 else 0
    risk_score = min(risk_score, 100)

    return {
        "target_domain": target_domain,
        "total_certificates": len(ct_results),
        "lookalike_domains": lookalikes[:20],
        "homoglyph_domains": homoglyphs[:20],
        "issuer_analysis": issuer_analysis,
        "wildcard_certs": wildcards[:10],
        "risk_score": risk_score,
        "risk_level": "HIGH" if risk_score >= 60 else "MEDIUM" if risk_score >= 30 else "LOW",
    }


if __name__ == "__main__":
    print("=" * 60)
    print("Certificate Transparency Phishing Detection Agent")
    print("crt.sh queries, lookalike detection, homoglyph analysis")
    print("=" * 60)

    domain = sys.argv[1] if len(sys.argv) > 1 else None

    if not domain:
        print("\n[DEMO] Usage: python agent.py <target_domain>")
        print("  e.g. python agent.py example.com")
        sys.exit(0)

    if not HAS_REQUESTS:
        print("[!] Install requests: pip install requests")
        sys.exit(1)

    print(f"\n[*] Querying crt.sh for: {domain}")
    results = query_crtsh(domain)
    print(f"[*] Found {len(results)} certificates")

    report = generate_report(domain, results)

    print(f"\n--- Lookalike Domains ({len(report['lookalike_domains'])}) ---")
    for l in report["lookalike_domains"][:10]:
        print(f"  [{l['similarity']:.3f}] {l['domain']} (issuer: {l['issuer'][:40]})")

    print(f"\n--- Homoglyph Domains ({len(report['homoglyph_domains'])}) ---")
    for h in report["homoglyph_domains"][:10]:
        print(f"  [diff={h['char_differences']}] {h['domain']}")

    print(f"\n--- Issuer Analysis ---")
    for issuer, count in sorted(report["issuer_analysis"]["issuers"].items(),
                                 key=lambda x: -x[1])[:5]:
        print(f"  {count:4d} | {issuer[:60]}")

    print(f"\n[*] Risk Score: {report['risk_score']}/100 ({report['risk_level']})")