The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's behavior. 1. Ingestion points: The skill reads PR check logs via the gh CLI and repository branch content via git as described in SKILL.md. 2. Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present when reading external data. 3. Capability inventory: The skill can modify files, perform git commits/pushes, and execute arbitrary project-specific commands (tests, builds, formatting). 4. Sanitization: The skill does not describe any sanitization or validation of the ingested logs or code content.
[COMMAND_EXECUTION]: The skill instructions direct the agent to execute project-specific formatting, testing, and build tools. This involves executing code defined within the repository, which is a standard development capability.

pr-ready