video-spec-builder
Warn
Audited by Snyk on Jul 6, 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). WeChat-article flow: when the operating user provides an
mp.weixin.qq.comURL, the skill calls an external API to convert the article to markdown and then ingests the extracted article body text/images into the runtime-generated video spec/HTML context (outsider-authored free text from the public WeChat article).
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill's WeChat-article flow explicitly runs a runtime curl against https://ideaflow-article-to-markdown.hf.space/resolve/mark to fetch/convert an mp.weixin.qq.com article to markdown which is then ingested to drive scene generation, so this external URL is used at runtime to control the agent's content pipeline.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata