brand-guidelines

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 0 "Context Ingestion" explicitly instructs the agent to fetch and analyze user-supplied public URLs and social media profiles (e.g., "Website URL", "Social media profiles" using WebFetch) and then uses those extracted signals as smart defaults that influence discovery, synthesis, and generated actions, which exposes the agent to untrusted third‑party content that could carry indirect prompt injection.