tavily

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill gives the agent direct access to stored credentials via ClawLink and explicitly exposes a "tavily_get_usage" action that can retrieve API keys/account usage, meaning the agent may need to read and output secret values verbatim (exfiltration risk).

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

• Third-party content exposure detected (high risk: 0.95). The required workflow uses Tavily actions like tavily_search, tavily_extract, and tavily_crawl, which at runtime fetch and ingest public web page/search result text authored by third parties into the agent’s LLM context (outsider-authored free text via web content extraction).

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs the agent to run npx @useclawlink/cli (which fetches and executes remote npm package code at runtime — https://www.npmjs.com/package/@useclawlink/cli) to connect to and control Tavily via ClawLink (https://claw-link.dev), so external code is fetched and executed and is required for the skill to function.