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 skill is a disclosed document fingerprinting helper that only mutates user-specified HTML files and writes a checksum file, with no evidence of hidden execution, persistence, exfiltration, or privilege escalation.
Install only if you want a document-integrity helper that can edit user-selected HTML files and create checksum files. Review the output before publishing, and be aware that the default timestamp format uses GMT+8 unless you pass a custom stamp.
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) |
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 embeds a long trigger list containing broad terms such as “时间戳”, “指纹”, “SHA256”, “fingerprint”, and “stamp”, which are common enough to match benign user requests outside the intended security/document-integrity workflow. This can cause unintended invocation of the skill, potentially steering unrelated conversations into copyright, provenance, or anti-tamper guidance and increasing the chance of inappropriate tool selection.
This file contains natural-language instructions and CLI help entirely in Chinese, and it defaults timestamp formatting to GMT+8. That imposes a specific language and locale on all users without opt-in, which matches the language/locale policy violation criteria.
This is a markdown file, so vague-trigger review applies. The file contains only licensing text and provides no invocation description, trigger phrases, scope constraints, or negative examples, leaving activation behavior entirely unspecified if this file is used as part of the skill’s descriptive materials.
The skill description is written entirely in Chinese and presents its usage and trigger phrases only in that language context, without offering any language-choice or opt-in behavior. This can indicate a locale/language constraint that is not documented as optional or region-specific.