grilling
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill features an autonomous 'fact-finding' mechanism that relies on processing untrusted user input to determine search targets.
- Ingestion points: Untrusted data enters the context via the user's plan, decision, or idea as defined in SKILL.md.
- Boundary markers: No specific delimiters or instructions are present to prevent the agent from following instructions embedded within the user's content.
- Capability inventory: The skill explicitly authorizes the agent to 'dispatch a sub-agent' to query the 'filesystem' and 'tools' to find facts without human confirmation.
- Sanitization: There are no sanitization or validation steps provided to filter the input before it influences the agent's autonomous data-gathering behavior.
Audit Metadata