Tp4
- Category
- MCP Tool Poisoning
- Confidence
- 98% confidence
- Finding
声明描述的是一个会对测试用例Excel进行实质性处理和转换的技能:筛选特定优先级、删除列、重新编号,并保留格式。实际代码却只是读取一个固定路径的Excel文件,访问名为“登录”的工作表,并打印第1行表头,没有进行任何筛选、删除、重编号或保存操作。其主要目的更像是检查表头结构,而不是按声明执行测试用例整理,因此属于明显的描述与行为不匹配。
- Content
Security audit
Security checks for vulnerabilities and agentic risk
This skill performs disclosed local Excel test-case filtering and formatting changes, with no evidence of hidden network access, persistence, credential use, or destructive behavior beyond the intended output workbook transformation.
Install only if you are comfortable with it creating modified output workbooks: it removes project/product columns, splits merged cells, filters rows, and rewrites case IDs. Keep the original workbook backed up, choose a distinct output filename, and avoid running the batch helper unless the hardcoded tmp folder contains only files you intend to process.
声明描述的是一个会对测试用例Excel进行实质性处理和转换的技能:筛选特定优先级、删除列、重新编号,并保留格式。实际代码却只是读取一个固定路径的Excel文件,访问名为“登录”的工作表,并打印第1行表头,没有进行任何筛选、删除、重编号或保存操作。其主要目的更像是检查表头结构,而不是按声明执行测试用例整理,因此属于明显的描述与行为不匹配。
声明描述的是一个对测试用例Excel进行实际加工处理的技能,核心功能包括筛选P0/P1、删除列、重新编号并保持格式。但提供的代码片段只是一个验证脚本:加载已生成的最终版Excel,检查“登录”sheet表头和总列数,并据此判断某列是否已删除。它的主要目的与声明不一致,属于结果校验而不是执行所声明的数据处理流程。因此应判定为描述与代码行为不匹配。
This markdown file documents behaviors that alter workbook structure and data layout, including deleting columns, splitting merged cells, and renumbering cases. Although these actions are core functionality, the README does not clearly warn users that the output file will be structurally modified and may not preserve formulas, merge semantics, or original identifiers.
The skill advertises file-processing behavior and includes code-oriented implementation guidance, but it does not declare any explicit tool scope such as permissions or allowed-tools. In an agent environment, missing scope boundaries can allow broader-than-necessary file access, increasing the risk of unintended reads of sensitive local files when the skill is invoked on user workbooks.
The manifest says the skill filters test-case Excel files, extracts P0/P1 cases, removes project/product columns, renumbers rows, and preserves formatting. This file merely opens a specific workbook, reads the first row of one sheet, and prints header values, with no filtering, column deletion, renumbering, or output generation.
The README presents the skill name, instructions, and example prompts entirely in Chinese, which can imply a fixed language requirement for invocation and use. There is no statement that other languages are supported or that Chinese is merely an example, so this may violate a language-choice policy.
This markdown file describes operations such as deleting columns, unmerging cells, renumbering rows, and saving a processed output file. Although L210 recommends backing up the original file, it does not explicitly warn users that the skill performs data-altering transformations that may affect workbook structure and content.
The manifest context states the skill should '删除项目/产品列' in addition to filtering P0/P1 cases and renumbering, but the package description string in setup.py only says it filters P0/P1 test cases, renumbers, and preserves formatting. This is a semantic mismatch in the skill's claimed behavior documentation.
The package description at L06 is written entirely in Chinese, which imposes a specific language in user-facing metadata. There is no indication that the skill is intentionally region-specific or that alternative language support is offered, so this appears to violate the language/locale policy criteria.
No suspicious patterns detected.