viral-video-copywriting
Warn
Audited by Snyk on Jun 15, 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). 方式A会在运行时对用户提供的抖音URL进行网页抓取/yt-dlp提取,随后把抓取到的标题/描述/字幕等“可读文本”进入智能体的分析与创作上下文;该文本属于抖音等外部发布者的内容(OUTSIDER)。
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The extract_douyin_video.py script fetches user-supplied Douyin video pages and subtitle JSON (e.g., https://www.douyin.com/video/7300000000000000000) at runtime via requests/yt-dlp and injects the retrieved text into the agent's analysis/prompting pipeline, so external content directly controls the agent's prompts.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata