case-business-case

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow ingests the evidence pack (research/), which contains outsider-authored quotes and facts collected during the research stage.

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

• Potentially malicious external URL detected (high risk: 0.70). The script fetches Mermaid from jsDelivr via CDN (https://cdn.jsdelivr.net/...) at runtime when drawing diagrams, constituting an inbound operational external dependency with unknown/third-party CDN provenance.