gpt-image2-ppt
Warn
Audited by Snyk on May 7, 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 explicitly ingests untrusted third-party content: SKILL.md and generate_ppt.py document a "template-clone" mode that accepts .pptx templates (including "网络下载") which render_template.py/template_analyzer read as per-page PNGs, and scripts/image_generator.py will download image URLs (http/https) returned by the model and feed reference images into prompt generation — meaning external, user-supplied web content is parsed and can materially influence subsequent prompt construction and image-generation actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata