grilling
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingest user-provided plans and designs which could potentially contain embedded instructions.
- Ingestion points: Processes user-supplied designs and plans.
- Boundary markers: No specific delimiters or instructions to ignore embedded content are provided.
- Capability inventory: The skill is instructed to 'explore the codebase', implying read access to local files.
- Sanitization: No explicit sanitization or validation of the input content is mentioned.
Audit Metadata