submittal-intelligence

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests untrusted third‑party submittal PDFs/data sheets/shop drawings via the document-intelligence skill and the /process-docs workflow (see "Parse Submittal Document" and "5a. Auto-Populated Compliance Matrix"), and the agent is expected to read and act on that extracted content to make compliance determinations and recommendations, which could allow indirect prompt injection.