serpapi

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

• Third-party content exposure detected (low risk: 0.10). The workflow involves executing searches across various engines (Baidu, Bing, Google, DuckDuckGo, eBay, etc.) via SerpApi, where search result contents and web pages ingested at runtime represent low-risk external content retrieval.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs execution of npx @useclawlink/cli, which fetches and runs external code from the npm package registry without an immutable digest or pinned cryptographic signature, constituting an unverifiable runtime external dependency.