omh-design-quality-gate

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a local command-line interface tool named 'omh' (e.g., omh runtime record --skill design-quality-gate) to manage and record the state of the design workflow.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes external design deliverables, including screenshots, PDFs, and web interfaces, which serves as an ingestion point for potentially malicious content. * Ingestion points: The skill ingests visual evidence and render observations through the visual_qa_evidence/v1 artifact type defined in SKILL.md. * Boundary markers: While the skill utilizes explicit status markers like not_observed and PASS, it does not include instructions to disregard potential prompt injections embedded within the visual data. * Capability inventory: The skill possesses the ability to execute the 'omh' CLI tool and manipulate workflow states (SKILL.md). * Sanitization: No sanitization, OCR filtering, or content validation mechanisms are specified for the external visual artifacts processed during the visual QA phase.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 08:33 PM
Security Audit — agent-trust-hub — omh-design-quality-gate