github-ops
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface.
- Ingestion points: The skill ingests untrusted data from GitHub via
gh issue list,gh pr list, andgh run view, which retrieve content (titles, bodies, logs) controlled by external contributors. - Boundary markers: The instructions lack boundary markers or explicit prompts to ignore instructions potentially embedded within the ingested GitHub data.
- Capability inventory: The skill grants the agent the ability to perform write operations, such as editing issues (
gh issue edit), commenting (gh issue comment), and creating releases (gh release create). - Sanitization: There is no evidence of sanitization or validation of external GitHub content before it is processed by the agent.
Audit Metadata