The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions guiding an agent on how to perform security audits. It does not contain any scripts, executable code, or platform-specific commands.
[PROMPT_INJECTION]: No attempts to override safety guidelines, bypass instructions, or extract system prompts were detected.
[DATA_EXFILTRATION]: There are no commands or instructions that access sensitive files or perform network exfiltration. The skill is designed for static analysis of user-provided data.
[REMOTE_CODE_EXECUTION]: No remote script downloads or dynamic execution patterns (like eval or exec) are present.
[EXTERNAL_DOWNLOADS]: The skill does not perform any network requests or external downloads.

review-security-headers-and-dependency-risk