Pinned Loading

1. socratic socratic Public

   self questioning skill for agents , claude code , codex etc

   121 18

2. detonate detonate Public

   Run untrusted AI tools in a sandbox and report what they actually do, not what their manifest claims.

   Go 11

3. asrt-bench asrt-bench Public

   Fire a frozen attack pack at your AI agent, verify what lands, and diff safety across versions.

   Python 1 1

4. reconRelate reconRelate Public

   ReconRelate is a CLI-first reconnaissance relationship mapper.

   Python 2

5. agent-structure agent-structure Public

   agent structure algorithms - a set of skills for making your agentic AI work algorithmically structured.

   Python 18 3

6. Hands-On-Ai-Security Hands-On-Ai-Security Public

   A Hands book on ai security from foundation to prompt injection, indirect prompt injection , offensive , defensive, agentic security .