brand-monitor

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

• Third-party content exposure detected (high risk: 0.90). The skill ingests and analyzes arbitrary public web content (e.g., via GET https://api.brand.dev/v1/brand/search and monitor results/mentions, which pull from "news", "blogs", "social", and "forums"), so the agent will read untrusted user-generated third-party content as part of its workflow.