omh-reliability-review
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill references a shell command (
omh runtime record) used for internal status tracking and telemetry within the Hermes platform harness. This is standard operational metadata for the environment. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data such as incident notes and SLO evidence. It mitigates injection risks by enforcing strict safety rules that require source-backed evidence before the agent can validate health or closure states. It specifically instructs the agent to separate assumptions from supplied metrics and incident notes.
- [SAFE]: No obfuscation, unauthorized network operations, credential harvesting, or privilege escalation patterns were detected. The skill uses standard reference loading mechanisms (
skill_view) to access common platform rules.
Audit Metadata