receiving-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external code review comments, which constitutes a vulnerability surface for indirect prompt injection attacks.
- Ingestion points: Review comments provided by users, external reviewers, or sub-agents.
- Boundary markers: The instructions lack explicit delimiters or markers to separate untrusted external comments from the system's reasoning path, although it suggests rephrasing as a verification step.
- Capability inventory: The skill utilizes shell-based search tools (
grep) and interacts with the GitHub API (gh api) to post replies. - Sanitization: There is no evidence of automated sanitization or filtering of the content within the review comments before the agent processes them.
Audit Metadata