Skip to content
Back to search

security-skills

SkillWorks with Gemini CLIGitHub

4000 security reports transformed to Skills you can use with Claude Code / Gemini CLI etc

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/instavm--security-skills/badge.svg)](/listings/instavm--security-skills)

HTML

<a href="/listings/instavm--security-skills"><img src="/api/listings/instavm--security-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Install with skills.sh (recommended)

npx skills add instavm/security-skills

Or install specific skills only:

npx skills add instavm/security-skills --skill mitm-find-idor

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 83 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Security Skills for CLI Agents
  2. A collection of security testing skills built from analyzing **4,000+ paid HackerOne bug bounty reports**. These skills can be used with Claude Code, Gemini CLI, or any agent that supports MCP/Skills.
  3. ## What is this?
  4. This repo contains specialized prompts (skills) that teach AI coding agents how to find real security vulnerabilities. Instead of dumping thousands of bug reports into context, each skill distills the patterns and techniques from hundreds of real-world findings into actionable guidance.
  5. ## Available Skills
  6. | Skill | Description |
  7. |-------|-------------|
  8. | `mitm-find-idor` | Find Insecure Direct Object Reference vulnerabilities |
  9. | `mitm-find-auth` | Detect authentication and authorization issues |
  10. | `mitm-find-bizlogic` | Identify business logic flaws |
  11. | `mitm-find-ssrf` | Find Server-Side Request Forgery vulnerabilities |
  12. | `mitm-find-sqli` | Detect SQL injection patterns |
  13. | `mitm-find-otp` | Find OTP/2FA bypass vulnerabilities |
  14. | `mitm-find-pii` | Identify PII exposure issues |
  15. | `mitm-find-secrets` | Detect leaked secrets and API keys |
  16. | `mitm-find-callback` | Find callback/webhook security issues |
  17. | `mitm-find-checksum` | Identify checksum/integrity bypass opportunities |
  18. | `mitm-find-enumerable` | Find enumerable endpoints and IDs |
  19. | `mitm-find-insecure` | Detect insecure configurations |
  20. | `mitm-find-referer` | Find referer-based vulnerabilities |
  21. | `mitm-list-apis` | List and analyze captured API endpoints |
  22. | `mitm-subdomains` | Analyze subdomain patterns |
  23. | `mitm-security-audit` | Run comprehensive security audit |
  24. | `mitm-report` | Generate security report |
  25. ## Setup
  26. ### Install with skills.sh (recommended)
  27. ```bash
  28. npx skills add instavm/security-skills
  29. ```
  30. Or install specific skills only:
  31. ```bash
  32. npx skills add instavm/security-skills --skill mitm-find-idor
  33. ```
  34. ## Usage
  35. 1. Start mitmproxy to capture traffic:
  36. ```bash
  37. mitmdump -w traffic.mitm --set flow_detail=3 2>&1 | tee log.txt &
  38. ```
  39. 2. Configure your browser/app to proxy through `localhost:8080`
  40. 3. Browse the target application to capture traffic
  41. 4. Ask your AI agent to analyze:
  42. ```
  43. Find security issues in example.com
  44. Check for idor and auth issues
  45. Run a full security audit
  46. ```
  47. ## How It Works
  48. Rather than overwhelming the AI with raw bug reports, each skill contains:
  49. - High-value patterns extracted from real bounty-winning reports
  50. - Specific grep/regex patterns to search traffic logs
  51. - Testing methodology with curl examples
  52. - Severity ratings and impact assessment
  53. - False positive guidance
  54. ## Disclaimer
  55. **Only use these tools on systems you have explicit permission to test.** Unauthorized security testing is illegal. These skills are intended for:
  56. - Authorized penetration testing
  57. - Bug bounty programs where you have permission
  58. - Security research on your own systems
  59. - Educational purposes
  60. ## Credits
  61. Built by analyzing 4,000+ paid bug bounty reports from [HackerOne's public disclosures](https://huggingface.co/datasets/Hacker0x01/hackerone_disclosed_reports).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.