qinyan-paper-analysis

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

• Third-party content exposure detected (low risk: 0.10). The agent skill analyzes academic papers by fetching PDFs or web pages via URLs supplied by the user, making outsider-authored content ingestion a low-risk active fetch.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill makes API calls to a third-party service at api.qinyanai.com, which is an unknown or third-party endpoint without established official provenance.