interface-review
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external repository sources which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill retrieves and processes PR titles and bodies (via
gh pr view), commit messages (viagit log), and source code content (viagit showandgit diff) as defined inscope-resolution.md. - Boundary markers: There are no instructions for the agent to use specific delimiters or to disregard embedded instructions within the PR descriptions or code content it analyzes.
- Capability inventory: The skill is restricted to using
gitandgh(GitHub CLI) for data retrieval and temporary worktree management; it does not have capabilities for arbitrary command execution or external network exfiltration beyond repository fetching. - Sanitization: The retrieved repository data is not sanitized or escaped before being presented to the agent for review.
Audit Metadata