The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the GitHub CLI tool (gh) for its primary functions.
Evidence: The file SKILL.md contains commands gh pr diff, gh pr view, and gh pr review to facilitate the PR review workflow.
[INDIRECT_PROMPT_INJECTION]: The skill acts as a consumer for untrusted data from GitHub pull requests, which could potentially contain malicious instructions.
Ingestion points: External content is ingested via gh pr diff and gh pr view in SKILL.md.
Boundary markers: The skill does not implement delimiters or specific instructions to disregard potentially malicious content within the PR diffs.
Capability inventory: The skill has the capability to write to the PR via gh pr review and access PR metadata.
Sanitization: No sanitization, filtering, or validation is performed on the data fetched from the PR before it is analyzed by the agent.

qe-pr-review