seedream

Warn

Audited by Snyk on Mar 10, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill's CLI and code explicitly accept arbitrary image URLs (--image) and can enable联网搜索/web search (--web-search) which sets a ContentGenerationTool for web_search in scripts/seedream.py (and SKILL.md documents the web-search option), meaning it fetches untrusted public URLs/content that will be interpreted as part of image-generation workflow and can therefore influence subsequent tool behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 06:07 PM