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 SSOT content-management methodology skill with no executable payload, persistence, credential handling, or hidden data flow found.
Before installing, note that this skill may trigger for broad content-maintenance questions and has a license notice that reserves rights over the documentation/theory text despite an MIT-style license file. From a security perspective, I found no code execution, persistence, credential access, or hidden network behavior.
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 manifest description defines very broad trigger conditions such as generic user complaints about content changing frequently, reducing rework, or updating one place to affect many outputs. Because the invocation scope is not tightly bounded, the skill may activate in contexts where SSOT guidance is only tangentially relevant, causing unintended routing, over-broad assistance, or interference with more appropriate domain-specific skills.
The file begins with a Chinese-only policy-style scope notice, while the remainder of the license is in English. This creates a language/locale constraint in a normative section without any opt-in, alternate language selection, or stated region-specific reason, which matches the policy-violation category for forced language.