competitor-monitoring

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to discover and ingest open/public third‑party content (see "Augment with web search", G2/Capterra discovery, and the column prompts for "Key People", "Recent Blog Posts", and "People LinkedIn Updates" that direct searching company websites, Medium/Substack, LinkedIn, news sites, etc.), and that research is used to drive enrichment, synthesis, and downstream actions—exposing the agent to untrusted user-generated web content that can influence behavior.