tavily-search

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md and the attached scripts (scripts/search.mjs and scripts/extract.mjs) call the Tavily API to fetch search results, an "answer", and raw content from arbitrary URLs/public web pages, and print those outputs for the agent to read and act on—clearly ingesting untrusted third-party/user-generated content that can influence subsequent decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's runtime Node scripts call https://api.tavily.com/search and https://api.tavily.com/extract and directly print/return the API's "answer" and extracted content (which would be injected into agent context), so these external URLs are used at runtime, their responses directly control agent-facing prompts, and the skill requires them.