code-reviewing
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from code diffs and project documentation, creating a surface for injection attacks.
- Ingestion points: The skill ingests untrusted data from git diff outputs, plan files, and PR descriptions as specified in Step 1 and Step 2 of SKILL.md.
- Boundary markers: While the skill utilizes separate sub-agent contexts in Step 3, there are no specific prompt delimiters or instructions to ignore embedded commands within the ingested data.
- Capability inventory: The orchestrator has the capability to automatically fix findings in Autopilot mode in Step 5, meaning injected instructions could lead to unauthorized code modifications or deletions.
- Sanitization: There is no evidence of sanitization, escaping, or filtering for the external code or documentation processed during the review axes.
Audit Metadata