deepstream-generate-pipeline

Warn

Audited by Snyk on Aug 16, 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). Step 3 ingests the user-authored natural-language query into scripts/generate_pipeline.py --query "<constructed_query>", which performs BM25 retrieval over the indexed CSV and returns the retrieved pipelines’ text into the assembly context.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 16, 2026, 05:53 PM
Issues
1
Security Audit — snyk — deepstream-generate-pipeline