deepstream-import-vision-model

Warn

Audited by Snyk on Jul 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.65). High: the required runtime workflow fetches outsider-authored model artifacts (e.g., HuggingFace/NGC repo files and config.json) and then ingests their contents into the agent’s LLM context via generated report text (markdown/HTML/PDF) that includes fields derived from those files (e.g., architecture/source/labels), creating an indirect prompt-injection surface.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 15, 2026, 05:41 AM
Issues
1
Security Audit — snyk — deepstream-import-vision-model