The Agent Skills Directory

[SAFE]: No malicious patterns were detected. The skill uses standard tools for its declared purpose.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes external PR data.
Ingestion points: PR comments and reviews fetched via gh pr view and gh api in SKILL.md.
Boundary markers: The instructions lack specific delimiters or headers to isolate external PR content.
Capability inventory: The skill utilizes Bash for CLI operations and Write for generating local documentation.
Sanitization: PR metadata and feedback are processed without explicit filtering or validation steps.

pr-retro