The Agent Skills Directory

[SAFE]: The skill is strictly instructional and diagnostic, providing patterns and guidance for an AI agent to audit code for common security vulnerabilities.- [SAFE]: No malicious behaviors such as data exfiltration, obfuscation, or unauthorized command execution were detected.- [SAFE]: The skill operates on local files and produces local documentation, following standard security auditing workflows.- [SAFE]: While the skill involves reading untrusted source code (Category 8: Indirect Prompt Injection), it lacks the high-risk capabilities (like network access or arbitrary code execution) that would make such an injection actionable or critical. The risk is consistent with the tool's primary purpose of code analysis.

sast-jwt