Skip to content
English

Switch theme

// Software stack

Security & red-team agents

Authorized vuln discovery, skill audits and agent defenses.

4 pieces4 setup stepsscenario: Let agents run safely

What goes in it

  1. 1

    SkillSpector Identity, secrets & agent security Open source

    Scanning

    Security scanner for AI agent skills.

    Or: agent-scan · AI-Infra-Guard · deepsec

    ★ 21k
  2. 2

    shannon Identity, secrets & agent security Open source

    Pen-testing (authorised)

    Autonomous white-box AI pentester for web apps and APIs.

    Or: hexstrike-ai · Decepticon

    ★ 49k
  3. 3

    trailofbits/skills Skills & rules Open source

    Security skills

    Trail of Bits Claude Code skills for security research.

    Or: security-audit-skill · Anthropic-Cybersecurity-Skills

    ★ 7.7k
  4. 4

    agent-governance-toolkit Identity, secrets & agent security Open source

    Governance

    AI Agent Governance Toolkit — policy, zero-trust identity, sandboxing.

    Or: destructive_command_guard

    ★ 6.4k

How to set it up

  1. 01Get the scope authorised in writing
  2. 02Scan skills and MCP servers first
  3. 03Run pen-test agents on an isolated network
  4. 04Share reports only with the security lead

⚠︎ For authorised testing only; unauthorised attacks are illegal.

Data updated: AI software & hot ranks · Solutions & stack guides(UTC+8)