omh-skill-health

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the omh CLI tool via the omh runtime record command to log workflow status and progress. This is a project-specific utility from the skill vendor used for operational tracking within the skill's defined lane.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize external data, which creates a potential attack surface for instructions embedded in processed content.
  • Ingestion points: The skill requires user request, target context, and observed failure signals as inputs, as defined in the 'Required inputs' section of SKILL.md.
  • Boundary markers: The skill contains explicit 'Safety rules' and 'Do Not Use When' constraints that establish a 'non-mutation boundary,' instructing the agent to differentiate between prepared guidance and observed evidence.
  • Capability inventory: The skill possesses the capability to execute shell commands (omh) and access local files (omh-routing/references/skill-common-rail.md) to retrieve shared operational rules.
  • Sanitization: The instructions do not define specific mechanisms for sanitizing, escaping, or validating the external data before it is interpolated into the agent's context or dashboard output.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 08:34 PM
Security Audit — agent-trust-hub — omh-skill-health