web-content-fetcher

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses arbitrary public URLs (via WebFetch/curl) and uses Playwright for social media sites like Twitter/X, Threads, and Instagram, then sends the extracted user-generated content to a Task agent for extraction/analysis, which exposes the agent to untrusted third‑party content that could carry indirect prompt injection.