The Agent Skills Directory

[SAFE]: This is a library skill consisting entirely of reference documents and a structural validation script. It does not perform any autonomous actions or handle user data directly.
[SAFE]: The shell script scripts/validate.sh performs basic file existence and content checks using controlled internal inputs; no untrusted data is passed to its execution context.
[SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or unauthorized remote code execution was found across the 23 analyzed files.
[SAFE]: The skill provides security-enhancing checklists (e.g., SQL safety, LLM trust boundaries, and race conditions) intended to improve the security posture of code generated by other agents.

standards