The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted content from external pull requests.
Ingestion points: Pull request details and code diffs are retrieved using gh pr view and gh pr diff in SKILL.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the retrieved PR content as untrusted data or to ignore embedded instructions.
Capability inventory: The agent has the capability to perform write operations by posting comments to the PR via gh pr comment.
Sanitization: There is no evidence of sanitization or filtering applied to the PR content before it is analyzed and acted upon.
[COMMAND_EXECUTION]: The skill utilizes shell-based commands to interact with the repository and the GitHub platform.
Evidence: The workflow involves executing gh pr view, gh pr diff, and gh pr comment to fetch and submit data related to the code review process.

pr-review