seedream-image
Warn
Audited by Snyk on Feb 20, 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.md explicitly states the skill performs "Real-time Web Search" and "联网触发" (auto-fetches trending/external info when prompts contain time-sensitive or hot-topic keywords), and reference.md lists external URLs, so the agent will fetch and interpret open/public third-party web content that can influence prompt-generation and subsequent actions.
Audit Metadata