grimoire-sout

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates by reading local documentation and interacting with the user. It does not perform network operations, access sensitive system files, or execute shell commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from other local skill files (grimoire-interrogator and grimoire-modeler) and user input. While this represents a potential surface for indirect prompt injection, the skill's capabilities are restricted to discussion and documentation, minimizing the risk of unauthorized actions.
  • [COMMAND_EXECUTION]: The skill explicitly includes a rule 'Never execute the user's objective', which serves as a safeguard against the agent attempting to run arbitrary commands based on user prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 08:28 AM