wfdata-search

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

• Third-party content exposure detected (low risk: 0.10). The workflow queries academic papers, patents, and articles from the Wanfang Data API (http://api.wfdata.com), which ingest third-party authored publications, abstracts, and full texts searched by the agent.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill references an external API base URL (http://api.wfdata.com) in its Python scripts to execute runtime queries against the Wanfang Data platform, which constitutes an external operational dependency with unknown/unverifiable first-party provenance.