vllm

Warn

Audited by Snyk on Aug 5, 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). In scripts/vllm-health, the runtime workflow sends HTTP GET requests (via --url, default http://127.0.0.1:8000) to /health, /version, /v1/models, /load, and a bounded read of /metrics and parses the returned bodies as free text/JSON from the remote server.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 5, 2026, 09:22 PM
Issues
1
Security Audit — snyk — vllm