enrich

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

• Third-party content exposure detected (high risk: 0.90). This skill's Enrichment Protocol (Step 4: "Web research" and "Social media lookup" and the Data Need table) explicitly instructs fetching and scraping untrusted public web and social-media content (Perplexity/Brave/Exa, platform APIs, web scraping) and using those results to update brain pages and drive actions, exposing the agent to potential indirect prompt injection from third‑party content.