competitive-monitoring

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and ingests content from arbitrary public competitor websites—e.g., via agent-browser open https://competitor.com/pricing and the Tavily crawl/map/extract API calls—reading page text, screenshots, and structured data for diffs and analysis, which exposes the agent to untrusted third‑party content that could carry injected instructions.