triage
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from GitHub issues and pull requests, creating a surface for indirect prompt injection. An attacker could craft issue content to manipulate the agent's analysis or proposed fixes.
- Ingestion points: The skill fetches external content using
gh issue view,gh issue list,gh pr view, andgh pr diffas described inSKILL.md. - Boundary markers: The instructions do not define clear delimiters or specific warnings to the model about ignoring instructions within the fetched data.
- Capability inventory: The skill has the ability to run shell commands via
gitandgh, including branch creation, commits, pushes, and labeling issues (SKILL.md). - Sanitization: No explicit sanitization or filtering of the fetched GitHub content is performed before processing.
Audit Metadata