find-overengineering
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to process untrusted external data (code diffs or subsystems) which could contain embedded malicious instructions.
- Ingestion points: Code diffs or subsystems provided by the user or read from the environment (SKILL.md).
- Boundary markers: Absent. The instructions do not specify how the agent should distinguish between code data and potential instructions within the diffs.
- Capability inventory: The skill grants the agent authority to make small rollbacks (file modifications) to the codebase immediately.
- Sanitization: Absent. There are no guidelines for validating or escaping content from the diffs before analysis.
Audit Metadata