serpapi

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

• Third-party content exposure detected (high risk: 0.85). SerpApi actions (e.g., serpapi_bing_search, serpapi_duck_duck_go_*, serpapi_event_search, serpapi_finance_search) fetch public web/search results at runtime and return them as JSON that the agent reads into its LLM context, which is outsider-authored free text from third-party sites/search engines.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs running npx @useclawlink/cli which fetches and executes remote code from the npm package (https://www.npmjs.com/package/@useclawlink/cli) at runtime to control agent actions and prompts, creating a required runtime external dependency.