enrichment-waterfall

Warn

Audited by Snyk on May 11, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly performs SerpAPI web searches and feeds the returned organic_results (public Google/LinkedIn search results) into the "LLM Extract (Stage 3)" information-extractor + Groq Chat nodes (see references/waterfall-template.json nodes "SerpAPI (Vendor 3)" and "LLM Extract (Stage 3)"), meaning untrusted public web/social content is ingested and interpreted by an LLM to decide enrichment and downstream actions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 11, 2026, 10:54 PM
Issues
1
Security Audit — snyk — enrichment-waterfall