release
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and process pull request titles, author metadata, and git commit logs to assist in drafting release notes.
- Ingestion points: Pull request metadata is retrieved via
gh pr listand commit history is accessed viagit login SKILL.md. - Boundary markers: The instructions do not define specific delimiters or warnings to isolate the ingested external content from the agent's primary instructions.
- Capability inventory: The skill utilizes
gh release create,gh pr create,git push, anduv sync, providing the agent with capabilities to modify the repository and manage releases. - Sanitization: There are no explicit steps provided for sanitizing or escaping the content retrieved from GitHub or Git before it is used in the release drafting process.
Audit Metadata