sf-einstein
Warn
Audited by Snyk on Jun 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The REQUIRED workflow includes multiple runtime web-fetches (“Web-fetch the Einstein Recommendations API reference…” and “Web-fetch Data Cloud connector setup…”) which can ingest outsider-authored public web content into the agent’s LLM context via fetched documentation pages.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata