worldmonitor-intelligence-dashboard

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly aggregates 435+ public RSS/API feeds (see src/feeds and api/feeds/aggregate.ts and FeedRegistry.register) and feeds those feedItems into the AI synthesizer (src/ai/synthesize.ts), so it fetches untrusted, third‑party content and ingests it into the agent's synthesis/correlation pipeline where that content can materially influence outputs and actions.