grilling
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied plans, decisions, or ideas which serve as untrusted data inputs.
- Ingestion points: User input describing the plan or idea to be grilled (SKILL.md).
- Boundary markers: Absent. The instructions do not define delimiters for user-provided plans or advise the agent to ignore instructions embedded within the user data.
- Capability inventory: The skill explicitly instructs the agent to explore the environment (filesystem and tools) to find facts related to the user's plan (SKILL.md).
- Sanitization: Absent. No validation or filtering of external content is mentioned.
Audit Metadata