The Agent Skills Directory

[SAFE]: The skill does not contain any prompt injection patterns, role-play instructions, or attempts to bypass safety filters.
[SAFE]: No network operations, external downloads, or sensitive file access patterns were detected. The skill operates as a static set of instructions for code analysis.
[SAFE]: Code examples in the reference documentation include security anti-patterns (e.g., hardcoded secrets, SQL injection) solely for educational purposes to assist the agent in identifying vulnerabilities during a review.
[SAFE]: No persistence mechanisms, privilege escalation commands, or obfuscated content were found in any of the skill files.
[SAFE]: Although the skill is designed to process untrusted code data, it lacks exploitable capabilities such as shell execution or network access, mitigating risks associated with indirect prompt injection.

code-review