what-shipped
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses standard command-line tools to retrieve repository metadata and history.
- Evidence: Employs
git status,git fetch,git log,gh pr list, andgh pr viewto gather state information from the local and remote repository. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external repository contributors which may contain untrusted instructions.
- Ingestion points: Extracted text from Pull Request titles, bodies, and commit messages using the
ghandgittools. - Boundary markers: Absent; there are no explicit delimiters used to isolate the data being summarized from the agent's core instructions.
- Capability inventory: The skill has the ability to read repository state and interact with common deployment services like Vercel, Render, or Cloudflare.
- Sanitization: Absent; the skill relies on the AI's standard processing rather than programmatic filtering of repository content.
Audit Metadata