patent-search
Warn
Audited by Snyk on Apr 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). This skill explicitly fetches public third‑party patent data (PatentsView API via patent_search.py and BigQuery via bigquery_search.py as described in SKILL.md/README) and instructs the agent to parse those JSON results and use them to drive follow-up actions and query refinement, so untrusted external content can materially influence agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata