omh-autopilot

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill manages the execution of build, test, and lint commands derived from the project's own configuration files (such as Makefiles or package.json). This is a standard and necessary function for an autonomous development tool to verify its work.
  • [PROMPT_INJECTION]: The skill has a standard attack surface for indirect prompt injection as it ingests project specifications, plans, and source code. These inputs are processed by sub-agents to guide the implementation.
  • Ingestion points: Reads files from .omh/specs/, .omh/plans/, and the local project workspace.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands when passing data to sub-agents.
  • Capability inventory: The skill can execute shell commands via omh_gather_evidence and delegate complex tasks to other skills.
  • Sanitization: No explicit filtering or sanitization of external content is mentioned in the procedures.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 09:18 AM
Security Audit — agent-trust-hub — omh-autopilot