market-intelligence
Warn
Audited by Snyk on Jun 20, 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’s runtime workflow explicitly uses Claude web_search to fetch “current market news” and “Reuters forex market analysis,” and then pipes the fetched page/text into sentiment/impact processing—i.e., outsider-authored public web content becomes LLM-readable context via the web_search results.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata