agentleFS
Sign inStart free
CodeWithBehnamCodeWithBehnam/cc-docs/skills/security-scan/SKILL.md

security-scan

Skill2 starsChanged 8 months agoMITView on GitHub

Scan the codebase for security vulnerabilities based on the OWASP Top 10. Use when the user asks to audit security, find vulnerabilities, check for security issues, or says "security scan", "audit this", "find security bugs".

We split this skill into the rules it gives an agent

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 74 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    A01 - Broken Access Control: Look for missing authorization checks, IDOR patterns, direct object references, insecure direct database …

    line 22
  2. Distinctive:

    A03 - Injection: Search for SQL queries built with string concatenation, unsanitized shell commands, template injection, LDAP injection, …

    line 26
  3. Distinctive:

    A05 - Security Misconfiguration: Check for debug mode enabled, verbose error messages exposing internals, permissive CORS headers, default …

    line 30
  4. Distinctive:

    A07 - Authentication Failures: Look for weak session management, missing account lockout, insecure password reset flows, JWT with weak or …

    line 34
  5. Distinctive:

    A08 - Software Integrity Failures: Check for use of untrusted CDN resources without integrity hashes, insecure deserialization of …

    line 36
  6. Distinctive:

    A09 - Logging Failures: Verify that authentication events are logged, that logs do not contain passwords or tokens, and that errors are …

    line 38

“Common” is measured: kept by at least 6 in 10 of the 74 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Context

  • Repository: !git rev-parse --show-toplevel 2>/dev/null || pwd
  • Languages detected: !find . -type f \( -name "*.py" -o -name "*.ts" -o -name "*.js" -o -name "*.go" -o -name "*.rb" -o -name "*.java" \) | sed 's/.*\.//' | sort | uniq -c | sort -rn | head -10
  • Target: $ARGUMENTS

Task

Perform a security audit of the codebase (or the path specified in $ARGUMENTS) covering the OWASP Top 10:

  1. A01 - Broken Access Control: Look for missing authorization checks, IDOR patterns, direct object references, insecure direct database access without ownership checks.
  2. A02 - Cryptographic Failures: Find hardcoded secrets, API keys, passwords in source code. Check for use of weak algorithms (MD5, SHA1 for passwords, ECB mode). Look for unencrypted sensitive data in logs or responses.
  3. A03 - Injection: Search for SQL queries built with string concatenation, unsanitized shell commands, template injection, LDAP injection, and XSS sinks.
  4. A04 - Insecure Design: Identify missing rate limiting on auth endpoints, no CSRF protection on state-changing forms, missing input length limits.
  5. A05 - Security Misconfiguration: Check for debug mode enabled, verbose error messages exposing internals, permissive CORS headers, default credentials in config files.
  6. A06 - Vulnerable Components: Note any obviously outdated dependency versions or known-vulnerable packages in package.json, requirements.txt, go.mod, or Gemfile.
  7. A07 - Authentication Failures: Look for weak session management, missing account lockout, insecure password reset flows, JWT with weak or no signature verification.
  8. A08 - Software Integrity Failures: Check for use of untrusted CDN resources without integrity hashes, insecure deserialization of user-supplied data.
  9. A09 - Logging Failures: Verify that authentication events are logged, that logs do not contain passwords or tokens, and that errors are logged without exposing stack traces to users.
  10. A10 - SSRF: Find URL parameters or user-controlled values passed to HTTP clients, file readers, or DNS lookups without validation.

For each finding, read the surrounding code to confirm it is a real issue, not a false positive.

Output Format

Executive Summary

Total findings by severity. One-paragraph risk assessment.

Findings

For each vulnerability:

  • ID: VULN-001, VULN-002, ...
  • Category: OWASP category (e.g., A03 - Injection)
  • Severity: Critical / High / Medium / Low / Informational
  • File: path/to/file.py:42
  • Description: what the vulnerability is
  • Evidence: the specific code snippet or pattern found
  • Remediation: concrete steps to fix it

No Issues Found

List categories where no issues were detected (to show coverage).

Out of Scope

Note any areas not checked (e.g., third-party libraries, infrastructure config not present in the repo).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free