The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes various shell commands using git and the GitHub CLI (gh). Specifically, it uses git merge-base, git diff, and git log to analyze code changes, and gh issue view and gh pr view to retrieve metadata. These commands are appropriate for a code-review skill.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection due to the way it processes external data.
Ingestion points: The skill reads untrusted data from commit messages via git log, issue comments via gh issue view <n> --comments, and pull request bodies via gh pr view --json body in SKILL.md.
Boundary markers: There are no explicit boundary markers or instructions to the subagents to ignore potential instructions embedded within the ingested GitHub metadata or diff content.
Capability inventory: The skill has the ability to execute shell commands (git, gh) and read arbitrary files within the repository (e.g., CLAUDE.md, AGENTS.md).
Sanitization: No sanitization, filtering, or escaping is performed on the data retrieved from GitHub or the git history before it is passed to the subagents for analysis.

code-review