grilling
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided plans, decisions, or ideas and interacts with the environment (filesystem) using sub-agents. If the input data contains malicious instructions, the agent may inadvertently follow them during the 'grilling' process.
- Ingestion points: User input regarding plans and ideas; files or environmental data retrieved by sub-agents.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the prompt instructions.
- Capability inventory: Accesses the filesystem and other tools through the invocation of sub-agents.
- Sanitization: No input sanitization or validation logic is defined.
Audit Metadata