research-web

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly performs multi-wave web research that fetches and ingests content from open/public third‑party sources (e.g., Wave 2: Stack Overflow, technical blogs, discussion forums; Wave 3: specialized forums/communities) and records/quotes those sources in the research log, exposing the agent to untrusted, user‑generated content that could carry indirect prompt injection.