omh-backend
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional, providing planning templates and checklists for backend API and schema design without executing any code or performing network operations.
- [SAFE]: It contains explicit security instructions, such as 'Never place secrets, tokens, or connection strings in the contract, examples, or handoff text' and 'Do not call databases, HTTP services, LLM, or network endpoints from OMH core'.
- [SAFE]: The 'Strong routing signals' section includes various languages (Japanese, Korean, Chinese) as legitimate triggers for the skill, with no evidence of homoglyph-based obfuscation or malicious intent.
- [SAFE]: The provided reference files (schema-migration.md, consumer-impact.md, service-contract.md) enforce industry best practices for data safety, backward compatibility, and authentication/authorization boundaries.
Audit Metadata