minium-test-generator
v1.0.0Minium 录制脚本转测试用例工具。自动解析录制脚本,生成符合规范的测试用例和页面对象,确保步骤完整、逻辑一致。
⭐ 0· 96·0 current·0 all-time
by@yiziria
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the included artifacts: Python scripts for parsing (parse_steps.py), validation (validate_steps.py) and generation (generate_pages.py), documentation and examples. The required capabilities (reading a recording file, inspecting a project directory, generating page/test files) align with the declared purpose. Minor inconsistencies: SKILL.md header version (11.0.0) differs from registry version (1.0.0) and some docs disagree on selector priority (most files prefer CSS→XPath, docs/项目基础规范.md lists XPath→CSS). These are quality issues, not indicators of malicious intent.
Instruction Scope
The SKILL.md explicitly instructs the agent to ask the user for a full path, check whether the directory exists, read existing project files, and (with user confirmation) create new files or append to existing ones. It also includes shell/PowerShell examples for checking paths (Test-Path) and suggests the user paste recording script content into the conversation. These behaviors are expected for a generator that integrates with a user's local project but are sensitive operations (reading arbitrary project files and writing to disk). The skill's guidance includes explicit confirmation steps before creating or modifying files, which mitigates risk. Also note some code in generate_pages.py is stubbed (pass) — the generator may be incomplete and may require running the provided scripts locally.
Install Mechanism
No install specification is present (instruction-only with bundled scripts). That is low-risk: nothing is pulled from the network or installed automatically. The package contains Python scripts which the user or agent can run; review those scripts before execution. No remote download URLs or archive extraction were found.
Credentials
The skill declares no environment variables, no credentials, and no config paths. All required operations (file parsing, generation, local checks) can be performed without secrets. The scripts expect certain project files to exist (base/basedef.py, base/basepage.py) which is justified by the stated purpose.
Persistence & Privilege
always: false; the skill is user-invocable and does not request permanent inclusion or modify other skills. It reads and writes files in a user-specified project path only after explicit confirmation per its own workflow. Autonomous invocation is allowed by default on the platform but does not combine with other red flags here.
Assessment
This skill appears to do what it says: parse Minium recording scripts and generate page objects and test files. Before installing or running it, consider the following:
- Review the bundled Python scripts locally (scripts/generate_pages.py, scripts/parse_steps.py, scripts/validate_steps.py) to ensure you understand what will be read and written. The code is local and there is no automatic network install, but you should still inspect it. Some generator functions are stubs/partial and the tool may need manual completion.
- The skill will ask for a full filesystem path and (per its instructions) will read your project directory structure and existing page/test files; be cautious about granting an automated agent filesystem access. Prefer to run the provided scripts yourself in a controlled environment (local machine or sandbox) rather than letting an autonomous agent execute shell commands on your system.
- Do not paste sensitive secrets or private configuration into the chat when sharing recording scripts; recording scripts can include business-specific selectors or flows. If the recording contains sensitive data, redact it before sharing.
- The SKILL.md mandates that the agent must ask for confirmation before creating or modifying files — keep that behavior and do not allow silent overwrites. Back up your project before running generation.
- There are minor documentation inconsistencies (selector priority differs between documents, SKILL.md version mismatch). Verify generated code follows your project's real conventions (basedef/basepage names and selector priority) and run validate_steps.py and your test suite on a branch/VM before merging.
If you want to proceed: run the scripts locally with your own Python interpreter and inspect the outputs, or let the agent operate only after you explicitly confirm the exact target directory and review the file list it will create/modify.Like a lobster shell, security has layers — review code before you run it.
latestvk97f51jjdpvfnw61rkzbc9bwkn83hfgy
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
