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 methodology skill with some packaging and routing quality issues, but no evidence of hidden execution, data theft, persistence, or destructive behavior.
Install only if you want a Chinese-first methodology prompt for recurring test-review-improve cycles. Be aware that the broad triggers may activate it too often, and the licensing terms should be treated as unclear because the package says both MIT and all-rights-reserved for different parts.
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) |
L009 将“.py 文件”表述为受 MIT 覆盖,L045 也写明 License: MIT;但 L098-L100、L116 又明确称本包无独立代码文件,且本包整体不适用任何代码许可、保留所有权利。这里不是单纯信息不全,而是同一技能文档对该技能资产许可范围给出了彼此冲突的意图说明。
The trigger keywords are extremely generic ('continuous', 'test', 'review', 'loop') and can match ordinary conversation unrelated to this skill. In an agent ecosystem, overly broad activation criteria can cause unintended skill invocation, prompt-routing errors, and context contamination, especially because this skill is methodology-oriented and could insert irrelevant process guidance into many tasks.
The manifest-level trigger_keywords are too generic to safely distinguish this skill from normal discussion, increasing the chance of accidental activation across unrelated prompts. While the skill is not overtly malicious, broad triggers enlarge its routing surface and can interfere with correct tool/skill selection, which is a real integrity risk in multi-skill agent environments.
The manifest description embeds a long trigger list containing broad, generic phrases such as '改进', '打磨', and '验证方案', which are common in many unrelated conversations. This can cause unintended skill invocation or routing collisions, making the assistant apply this methodology in contexts where it was not explicitly requested, reducing reliability and potentially bypassing more appropriate skills.
SQP-3 applies to all file types and covers language or locale policy violations. The explanatory licensing notice is presented in Chinese with only limited inline English glosses, and the file does not offer an alternative language version or indicate that the Chinese-only presentation is required for a specific regional context.
This file is a markdown file, so SQP-1 applies. Line L07 defers key applicability details to another document section instead of making the boundaries self-contained here, which can create ambiguity about the exact scope and constraints of the licensing statement in this file.
L056-L064 主动宣称‘识别用户输入语言,自动用同语言回复’等运行时能力,但整份技能文件从 L098、L116 还说明这是‘纯文档/理论件’、无独立代码文件。该表述把未实现的能力写成既有功能,构成文档意图与实际内容的不一致。
The manifest description is entirely in Chinese and does not indicate that language selection is optional or that the skill is intentionally limited to Chinese-speaking users. This can violate language/locale policy when no user opt-in or justification is provided.