Incomplete referenced artifact analysis
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md command: 'node scripts/video2text/index.js --file "https://example.com/video.mp4"'
Security audit
Security checks for vulnerabilities and agentic risk
The verdict is benign with medium confidence: scanners found no reported malicious behavior, but some code could not be fully inspected, so the evidence is incomplete.
The verdict is benign, but the scan was partial: 11 of 20 components were only partly inspected. If you install, consider whether the environment-variable access and automatic cleanup described by the scanner fit your needs, and review the skill's permissions and cleanup behavior where possible.
Referenced artifact was not completely inspected
command: 'node scripts/video2text/index.js --file "https://example.com/video.mp4"'
Referenced artifact was not completely inspected
command: 'node scripts/video2text/index.js --file "/path/to/video.mp4"'
Referenced artifact was not completely inspected
command: 'node scripts/video2text/index.js --file "https://example.com/video.mp4" --prompt "总结这个视频的核心观点"'
Referenced artifact was not completely inspected
command: 'node scripts/video2text/index.js --file "/path/to/video.mp4" --prompt "改写成小红书风格的文案"'
Referenced artifact was not completely inspected
command: 'node scripts/video2text/index.js --id last --prompt "提取视频中的所有金句"'
Referenced artifact was not completely inspected
command: 'node scripts/video2text/index.js --help'
Referenced artifact was not completely inspected
| 怎么把 https://example.com/video.mp4 里的声音转成文字 | `node scripts/video2text/index.js --file "https://example.com/video.mp4"` |
Referenced artifact was not completely inspected
| 总结这个视频的核心观点 https://example.com/video.mp4 | `node scripts/video2text/index.js --file "https://example.com/video.mp4" --prompt "总结这个视频的核心观点"` |
Referenced artifact was not completely inspected
| 把本地 /path/to/video.mp4 改成小红书文案 | `node scripts/video2text/index.js --file "/path/to/video.mp4" --prompt "改写成小红书风格的文案"` |
Referenced artifact was not completely inspected
| 用刚才分析的视频提取所有金句 | `node scripts/video2text/index.js --id last --prompt "提取视频中的所有金句"` |
Referenced artifact was not completely inspected
| 分析这个视频的情感基调和受众 | `node scripts/video2text/index.js --file "<URL或路径>" --prompt "分析视频的情感基调和目标受众"` |
Referenced artifact was not completely inspected
node scripts/video2text/index.js --file "/path/to/your/video.mp4"
Referenced artifact was not completely inspected
node scripts/video2text/index.js --file "https://example.com/video.mp4"
Referenced artifact was not completely inspected
node scripts/video2text/index.js --file "/path/to/your/video.mp4" --prompt "请用三个要点总结这个视频的核心内容"
Referenced artifact was not completely inspected
node scripts/video2text/index.js --file "/path/to/your/video.mp4" --prompt "将这段内容改写成一篇风趣幽默的小红书文案"
Referenced artifact was not completely inspected
node scripts/video2text/index.js --id last --prompt "提取视频中的所有金句"
Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
4. 同时传入文件路径与任务ID,优先执行 `--id`,忽略 `--file`
5. 无自定义 prompt 时,默认完整转录视频全部文字
| 用户自然语言指令 | 自动生成命令 |
| -------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------- |
| 视频提取 https://example.com/video.mp4 中的文字 | `node scripts/video2text/index.js --file "https://example.com/video.mp4"` |
| 把本地 /path/to/your/video.mp4 改成小红书风格的文案 | `node scripts/video2text/index.js --file "/path/to/your/video.mp4" --prompt "改写成小红书风格的文案"` |
Without declared permissions the skill's intent is opaque and cannot be validated.
The script invokes clean.deleteExpire() before checking arguments or handling help, without a confirmation, user-facing log, or explanatory comment. This deletion-oriented maintenance operation is not an obvious part of requesting video transcription, and its errors are silently suppressed.