Ae1
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | 文档与理论文本 | 本 `SKILL.md`、`README.md`、其中「理论依据」段与一切理论表述 | **不在 MIT 覆盖范围内**:保留所有权利(All rights reserved) |
Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only skill about video watermarking and ownership proof, with no hidden code execution, persistence, or data exfiltration behavior found.
Review the broad activation terms and the unusual license split before installing. The skill appears safe from a security perspective, but it may trigger on general video or watermark questions and its documentation is not actually covered by the MIT license despite the package metadata saying MIT.
Referenced artifact was not completely inspected
| 文档与理论文本 | 本 `SKILL.md`、`README.md`、其中「理论依据」段与一切理论表述 | **不在 MIT 覆盖范围内**:保留所有权利(All rights reserved) |
The trigger keywords are extremely generic ('video', 'anti', 'theft') and can cause the skill to activate in many unrelated conversations. Overbroad activation increases the chance of unintended routing, context hijacking, or the injection of irrelevant policy/content into sessions where the user did not request this skill.
The manifest embeds a long trigger list with broad generic terms such as 'watermark', '加水印', and '版权保护' that can match common user requests outside the narrowly intended anti-theft context. This can cause the skill to be invoked unexpectedly, increasing prompt-surface exposure and the chance that unrelated conversations are routed into this skill's instructions or outputs.
The file begins with a Chinese-only scope notice while the rest of the license text is in English, creating a language-specific policy issue in natural-language content. There is no indication that the Chinese wording is optional, translated elsewhere, or required for a region-specific purpose.