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
The package claims to help extract old Word .doc files, but the inspected skill contains governance, branding, and licensing text rather than usable extraction instructions or code.
Review before installing. This does not appear to be malware, but it also does not provide the promised .doc extraction method; install only if you are comfortable with a documentation-only package and broad trigger wording, and prefer a version that adds real extraction steps or code with narrower activation scope.
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 advertises a reliable .doc extraction skill, but the file contains only governance, branding, and licensing text with no operational instructions or implementation. This is dangerous because agents or users may invoke the skill expecting document-processing behavior and instead receive misleading metadata-only content, creating integrity and supply-chain trust issues in automated skill selection.
The manifest lists generic trigger keywords like "doc", "legacy", and "extract" without clarifying the activation context, scope limits, or negative examples. These terms are common enough to overlap with ordinary document-related requests and could cause unintended invocation of this skill.
The license section explicitly states there are no independent code files and that the package is purely documentation, which contradicts its presentation as a functional extraction skill. This inconsistency can be exploited to deceive downstream systems, reviewers, or users about available capabilities, undermining trust and potentially causing unsafe automation decisions based on nonexistent functionality.
The manifest description includes multiple broad trigger phrases such as '提取 doc 全文', '法规 doc 附件', and generic parser/tool names, which can cause the skill to activate outside the narrowly intended use case. Over-broad activation increases the chance that unrelated document-processing requests are routed to this skill, creating misfires, incorrect handling of inputs, or unsafe processing paths if later automation assumes the skill is appropriate.
The file begins with licensing and scope statements only in Chinese, with limited English parenthetical fragments, which imposes a language constraint on critical usage terms. Under the policy, language restrictions should either offer a language choice or clearly justify the locale-specific requirement, neither of which is present here.
The skill description is entirely in Chinese and frames usage around Chinese regulatory sources, but it does not indicate whether this language constraint is intentional, optional, or user-selectable. This can be a natural-language policy concern if the skill is expected to serve users across locales without forcing a specific language context.