tavily-market-research

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

• Third-party content exposure detected (low risk: 0.10). The Tavily market research workflow searches and ingests arbitrary web pages, search results, analyst reports, and news articles containing outsider-authored free text via search tools.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill references external skills via npx skills add tavily-ai/skills --skill <name>, constituting an inbound operational dependency on an external package registry and repository.