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
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata