relight

Warn

Audited by Snyk on Aug 13, 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). The required runtime workflow is the RunComfy CLI invocation with user-supplied JSON --input containing a prompt string (outsider-authored text) that is sent to the Qwen Edit relight model for generation, and thus the agent ingests indirect prompt text at runtime.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 13, 2026, 10:57 AM
Issues
1
Security Audit — snyk — relight