tavily-monitor

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

• Third-party content exposure detected (low risk: 0.10). The agent monitors search results and web pages using Tavily, ingesting arbitrary outsider-authored web content and search snippet text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill references tavily-ai/skills via npx skills add, which is an unofficial community-maintained GitHub repository locator functioning as an operational dependency, placing it in the medium tier.