Sales

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

• Third-party content exposure detected (high risk: 0.90). The workflows explicitly accept and process external URLs (e.g., "Step 1: Gather Input" in Workflows/CreateNarrative.md accepts a "URL to product page" and the required steps invoke the StoryExplanation skill "for [input content]"), meaning the agent will fetch and interpret public third‑party web content as part of its pipeline and that content can change downstream decisions (narrative, visuals, prompts).