prospecting
Warn
Audited by Snyk on Aug 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). Skill “prospecting” ingests outsider-authored free text at runtime by browsing/extracting prospect content from third-party sources like Google Maps/Yelp search results (discovery) and then optionally programmatically reading individual business websites via Firecrawl/Browserbase, where the page text is directly supplied to the LLM.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata