srt-hyperframes-editorial-video

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). 运行时 LLM 上下文会读取用户提供的 SRT 字幕文本（srtPath → generate-storyboard.mjs/storyboard SubAgent 解析并生成 storyboard.json，再驱动后续 creator 分片），而该 SRT 属于非本组织作者的外部自由文本输入。

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill repeatedly invokes "npx hyperframes" at runtime (e.g., npx hyperframes --version, npx hyperframes lint/inspect/render), which will fetch and execute the HyperFrames package from the npm registry (e.g. https://registry.npmjs.org/hyperframes), and the workflow requires that CLI as a runtime dependency — meaning remote code would be fetched and executed during runtime.