grilling
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied plans or decisions and directs the agent to 'dispatch a sub-agent' to find facts from the environment (filesystem, tools, etc.) related to that input. This creates a surface where instructions embedded in the user's plan could influence the sub-agent's behavior.
- Ingestion points: User input describing a plan, decision, or idea (SKILL.md).
- Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from obeying instructions embedded in the user's data.
- Capability inventory: The skill explicitly enables the use of sub-agents to access the local filesystem and other tools (SKILL.md).
- Sanitization: There is no evidence of sanitization or validation for the 'facts' the agent is instructed to find.
Audit Metadata