Skill of Skills
📚 resourceActivePromisingcritical

Pentest-Swarm-AI

by Armur-Ai

Autonomous penetration testing using a swarm of AI agents. Orchestrates recon, classification, exploitation, and reporting specialists with ReAct reasoning — supports bug bounty, continuous monitoring, and CTF modes. Built with Go, Claude API, and 7+ native security tools.

Stars

1.8k

Skill Type

⚙️ Infrastructure Operations

Quality Score

105/200

License

Apache-2.0

Forks

362

Last Updated

Jun 11, 2026

Discovered

Apr 3, 2026

Validation

Passed

github.com/Armur-Ai/Pentest-Swarm-AI

Quality Breakdown

105/ 200

Content Signals

○Gotchas/Edge Cases+40
✓Progressive Disclosure+30
○Trigger Description+20
○Verification/Safety+20
✓Code Examples+15
✓Composability+15

Repo Health

✓Recent Activity+15
✓Scripts/Automation+10
✓Real Usage (Issues)+10
✓Single Responsibility+10
✓Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

critical

Manual security review required. Use with extreme caution.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Autonomous penetration testing swarm with multi-agent orchestration without explicit human approval gates
  • Exploit execution capability (internal/agent/exploit/executor.go) - executes arbitrary security exploits autonomously
  • Shell command parsing and execution (internal/agent/exploit/shellparse.go, executor.go) enabling remote code execution
  • Designed for autonomous operation across multiple modes (bug bounty, continuous monitoring, CTF) with minimal intervention
  • Integrates 7+ native security tools with autonomous invocation and chainable payloads
  • Swarm agents spawn and coordinate independently (orchestrator/agent.go) without human-in-the-loop approval