The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted data from external GitHub pull requests, creating a surface for indirect prompt injection where malicious instructions in a PR could attempt to influence agent behavior.
Ingestion points: Pull request metadata and code diffs fetched via gh pr view and gh pr diff in SKILL.md.
Boundary markers: Absent; there are no instructions to the agent to treat the PR content as untrusted or to ignore embedded commands.
Capability inventory: The skill utilizes gh CLI for read operations and can perform write operations by posting comments via gh pr review.
Sanitization: No sanitization or validation of the fetched PR content is specified before analysis.

github-review