reviewing-code
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external code files to provide implementation feedback, which exposes the agent to instructions hidden within the data being analyzed.
- Ingestion points: Local source files accessed via Read, Grep, and Glob tools.
- Boundary markers: The instructions lack explicit delimitation or warnings to ignore instructions embedded within the code context.
- Capability inventory: Utilizes file system discovery and reading tools alongside a specialized agent spawning tool (mcp__codex__spawn_agent).
- Sanitization: No sanitization of ingested code content is performed before processing.
Audit Metadata