grill-me
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The instruction to explore the codebase to answer questions creates an indirect prompt injection surface. Malicious content within the repository could attempt to influence the agent's behavior during the design review.
- Ingestion points: Local codebase files accessed during the session.
- Boundary markers: Absent; no instructions provided to ignore or delimit embedded instructions in codebase files.
- Capability inventory: Codebase exploration and file reading.
- Sanitization: Absent; no validation or filtering of codebase content is performed.
Audit Metadata