grilling
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch facts from the environment, including the filesystem and tools, which creates a surface where the agent might ingest untrusted data containing malicious instructions.
- Ingestion points: Local filesystem and tool outputs accessed during fact-finding rounds as described in SKILL.md.
- Boundary markers: None. The instructions lack delimiters to isolate data from instructions when fetching environment facts.
- Capability inventory: The agent is empowered to dispatch sub-agents to explore the environment and interact with system tools.
- Sanitization: The skill does not provide mechanisms to sanitize or validate content retrieved from the environment.
Audit Metadata