story-cover
Warn
Audited by Snyk on Aug 24, 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). 必需运行流程在 Step 3/4 中只把“用户输入的书名/作者名/参考图URL或本地路径(若提供)”拼进提示词并发送给 GPT-Image-2(含对 REF_IMAGE 的 URL 下载载入、以及将书名/作者名直接嵌入到 Title text/Author name),属于无先选择特定条目的直接消化自由文本。
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata