omh-parallel-tools
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests local environment metadata and version information to perform its workflow. This creates a surface where data in those files could influence agent behavior, though the skill mandates safety measures to mitigate risk.
- Ingestion points: Local configuration metadata and Hermes version information (SKILL.md).
- Boundary markers: None explicitly defined to separate data from instructions during ingestion.
- Capability inventory: Execution of 'omh' CLI tool and modification of local '.env' and configuration files.
- Sanitization: Instructions explicitly specify redacting secrets and using placeholders in diffs, and require explicit user approval before applying changes.
Audit Metadata