grill-me
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to gather facts from the environment, such as the filesystem and available tools, to inform its "design tree" interview process.
- Ingestion points: Environment facts (filesystem and tools) fetched by sub-agents, as well as user responses to interview questions in
SKILL.md. - Boundary markers: The skill does not define any delimiters or instructions for the agent to differentiate between data and instructions when processing environment facts.
- Capability inventory: The skill explicitly requires the agent to utilize filesystem access and tool execution capabilities via sub-agents.
- Sanitization: There are no instructions for validating, filtering, or escaping the content retrieved from the environment or provided by the user before it is used to reshape the design tree.
Audit Metadata