grill-me
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted data. 1. Ingestion points: Facts retrieved from the filesystem, code, tools, docs, and the web via subagents in SKILL.md. 2. Boundary markers: The instructions lack explicit delimiters or 'ignore' instructions for retrieved data. 3. Capability inventory: The skill can trigger the 'handoff' utility to write files (SKILL.md). 4. Sanitization: No sanitization steps are defined for external data.
- [COMMAND_EXECUTION]: The skill utilizes tool calls and subagent dispatching to perform environment lookups and state preservation as part of its normal operation (SKILL.md).
Audit Metadata