github-code
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from external sources. \n
- Ingestion points: The agent reads linked issues, PR bodies, conversation threads, inline comments, and repository source code, as described in
references/workflow.md. \n - Boundary markers: There are no specified delimiters or instructions to prevent the agent from following commands embedded within the external data. \n
- Capability inventory: The skill has significant write capabilities, including
git push,gh workflow run,github_createPullRequest, andgh apifor pull request interactions, as detailed inreferences/api-surface.md. \n - Sanitization: No specific technical sanitization or validation mechanisms are defined for the untrusted data being processed, although a policy exists to prevent leaking sensitive information into public PRs.
Audit Metadata