grill
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content (plans, decisions, or ideas) and uses that information to drive its questioning logic and fact-finding missions.
- Ingestion points: User-provided plans, decisions, or ideas described in
SKILL.md. - Boundary markers: Absent; the skill does not instruct the agent to use delimiters or ignore potentially malicious instructions within the user-provided plan.
- Capability inventory: The skill authorizes the use of sub-agents to access the environment, including the filesystem and other tools, to gather facts as described in
SKILL.md. - Sanitization: Absent; no sanitization or validation of the user's input plan is described.
Audit Metadata