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/v1artifact type defined in SKILL.md. * Boundary markers: While the skill utilizes explicit status markers likenot_observedandPASS, 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