The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from git logs, commit messages, and pull request information which could contain adversarial content designed to influence the agent's behavior during the investigation.
Ingestion points: The skill uses git log, git blame, git show, and gh pr view to retrieve external data.
Boundary markers: Absent. There are no instructions to use delimiters or to disregard instructions found within the code history.
Capability inventory: The skill has access to Bash (scoped to git), Read, Grep, and Glob tools.
Sanitization: Absent. Content from history is processed without filtering or validation.

git-investigate