grilling
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided plans or ideas and explicitly instructs the agent to explore the environment, including the filesystem and available tools, to verify facts. This capability creates a potential attack surface where instructions embedded in processed files could influence agent behavior.
- Ingestion points: User-provided descriptions of plans, decisions, or ideas, as well as files found in the environment (filesystem).
- Boundary markers: No explicit delimiters or instructions to ignore embedded content are present in the skill definition.
- Capability inventory: The skill utilizes filesystem access and general tool execution to "look up facts."
- Sanitization: There is no evidence of sanitization or validation of the content retrieved from the environment before it is processed by the agent.
Audit Metadata