github-comment-triage
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill instructions are limited to organizational workflows and use basic file-reading tools.
- [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by processing untrusted data from GitHub pull request comments. * Ingestion points: Step 1 of the workflow in SKILL.md specifies collecting all open review threads and inline comments. * Boundary markers: The instructions do not define delimiters or provide warnings to ignore commands embedded within the comments. * Capability inventory: The skill is restricted to the tools Read, Glob, and Grep as defined in SKILL.md, minimizing the risk of harmful actions if an injection occurs. * Sanitization: No input validation or sanitization of the comment data is described in the workflow.
Audit Metadata