The Agent Skills Directory

[SAFE]: The skill instructions are purely focused on text generation and adherence to project-specific Pull Request templates. It does not perform network operations, file system modifications, or command execution.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data from git diffs which could contain malicious instructions hidden in code comments. However, the output is limited to drafting human-readable PR descriptions, posing no direct threat to the execution environment. [Ingestion points: git diff, branch names; Boundary markers: Not explicitly defined; Capability inventory: Text generation only; Sanitization: None].

pr-description