omh-instinct-ledger
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust review-based workflow for promoting learned patterns, explicitly forbidding autonomous modifications to the host environment, skills, or memory.\n- [SAFE]: Defensive examples are provided to guide the agent in rejecting requests for silent or unauthorized actions, such as installing hooks or mutating global skills.\n- [SAFE]: The skill uses local tracking mechanisms (e.g., '.curator_ledger.jsonl' and 'omh runtime') that are consistent with its stated purpose of project optimization and lesson tracking without external network dependencies.
Audit Metadata