grilling
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided content such as plans, decisions, or ideas. It then uses tools, sub-agents, and filesystem access to verify facts related to this content.
- Ingestion points: User input provided during the "grilling" process (SKILL.md).
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are present when processing user-provided ideas.
- Capability inventory: Access to the filesystem, general tools, and the ability to dispatch sub-agents to perform lookups (SKILL.md).
- Sanitization: No explicit sanitization or validation of the user-provided data is mentioned before it is used to drive automated fact-finding missions.
Audit Metadata