seedream-image

Warn

Audited by Snyk on Mar 2, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.85). The skill's workflow and scripts explicitly ingest untrusted third-party content: SKILL.md/reference.md state it will "auto-fetch" trending info for time-sensitive prompts and accept/upload external reference images, and generate.py (CLI --image-urls and download_image) downloads arbitrary image URLs which are then used to drive prompt construction and API generation—so public/web content can directly influence agent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 2, 2026, 07:29 AM