grilling
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to autonomously fetch facts from the environment (filesystem and tools) to supplement the user's input. This creates an attack surface where malicious content stored in files or tool outputs could influence the agent's behavior.
- Ingestion points: The skill explicitly directs the agent to query the environment (filesystem, tools) in
SKILL.mdwhen a frontier question requires facts. - Boundary markers: The instructions lack delimiters or explicit warnings to the agent to disregard instructions that might be embedded within the retrieved environmental data.
- Capability inventory: The skill permits the agent to spawn sub-agents for environment exploration and tool usage across the filesystem.
- Sanitization: There is no mention of sanitization, validation, or filtering of the content retrieved from the external environment before it is processed as a fact.
Audit Metadata