grill-minimal
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied plans, decisions, or ideas which acts as an ingestion point for potentially untrusted data that could influence the agent's behavior.
- Ingestion points: User input passed via the <plan, decision, or idea> argument.
- Boundary markers: The instructions do not define boundary markers or delimiters to wrap the user-provided content.
- Capability inventory: The skill is designed to invoke the grill-with-docs skill and can resolve additional skills using productivity:resolving-user-invoke-skills.
- Sanitization: No sanitization or validation of the input is specified before the data is processed or delegated.
Audit Metadata