motion

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The workflow’s Codex and audit/preview steps fetch provider-authored documentation/resources (e.g., search-motion-docs, Motion+ resource links, and gated Motion+ methodology/source) rather than consuming arbitrary outsider-submitted free text without first selecting a specific resource/tool result.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches Motion+ resources at runtime (e.g., motion://skills/performance-audit and the motion://docs/{platform}/{id}, motion://examples/{platform}/{id}, motion://ui/react/{id} resource links) which the agent must read and follow exactly and which can deliver paste-ready source that directly controls the agent's outputs.