qe-code-review-quality
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection by design, as its primary function is to process untrusted data from external code repositories.
- Ingestion points: The skill facilitates analysis of Pull Requests and changed files via data fields like
prNumberandprFilesmentioned in the Agent-Assisted Reviews section ofSKILL.md. - Boundary markers: The instructions do not define explicit boundary markers or "ignore instructions" delimiters to prevent the agent from following malicious commands embedded in the code being reviewed.
- Capability inventory: The skill orchestrates multiple sub-agents (
qe-quality-analyzer,qe-security-scanner, etc.) which perform file analysis and logic evaluation. - Sanitization: There is no evidence of input sanitization or instruction filtering for the content of the files being reviewed.
Audit Metadata