tiktok-gemini-video-workflow
Fail
Audited by Snyk on Aug 14, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E005: Suspicious download URL detected in skill instructions.
- Suspicious download URL detected (high risk: 0.70). The GitHub URL points to a third‑party personal repository that the Skill instructs to clone/build (which can run arbitrary code) and thus is potentially risky, while the other two URLs are official Google sites and low risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). 该工作流在运行时会通过
lark-cli base +record-download-attachment读取飞书多维表中“爆款视频/产品图”附件并对其进行逐帧转写与抽帧处理,同时还会读取“验收意见”等文本字段内容用于返工逻辑,因此飞书表单/评论式输入中的外部免费文本(由飞书用户作者)会进入 LLM 处理链。
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill explicitly runs a runtime installation/build sequence that clones and builds remote code from https://github.com/GargantuaX/gemini-watermark-remover.git (git clone + pnpm install/build + node scripts), which fetches and executes third‑party code the Skill relies on.
Issues (3)
E005
CRITICALSuspicious download URL detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata