grilling
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to autonomously fetch facts from the local environment.
- Ingestion points: The agent is instructed in
SKILL.mdto find facts from the "filesystem, tools, etc." to resolve decision tree prerequisites. - Boundary markers: No delimiters or safety instructions are specified to prevent the agent from following directives embedded within the data it retrieves.
- Capability inventory: The skill grants the agent the ability to browse the "filesystem" and use environment "tools" via sub-agents.
- Sanitization: The instructions do not define any validation or sanitization steps for data collected from the environment before it influences the agent's behavior.
Audit Metadata