grill-me
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its processing of untrusted content.
- Ingestion points: User-provided plans, designs, and the local codebase.
- Boundary markers: Absent; there are no instructions to disregard commands embedded in data.
- Capability inventory: Filesystem read access (implied by codebase exploration).
- Sanitization: Absent; the skill does not validate or filter the ingested content.
Audit Metadata