The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from external sources including local git diffs and remote GitHub Pull Request information.
Ingestion points: Data from git diff --name-only and gh pr view is ingested into the agent context (SKILL.md).
Boundary markers: The instructions do not specify any delimiters or warnings to ignore instructions embedded within the code changes or PR descriptions.
Capability inventory: The skill utilizes the git and gh CLI tools and delegates analysis to multiple autonomous specialized agents (SKILL.md).
Sanitization: There is no mention of sanitizing or escaping the content retrieved from the PR or code files before it is processed by the review agents.

review-pr