patent-claim-analyzer
Warn
Audited by Snyk on Jun 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). The skill calls outsider-authored free text from the public patent-claims database via runtime API responses (Zhihuiya endpoints
claimData/claimDataTranslated/bibliography), and then injects that returned claim text into the LLM context as part of the generated markdown report.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata