Skill Install Checker
v1.0.0安装前验证二进制、环境变量、配置、OS 与 sandbox 条件，解释为什么此机不适合装。；use for skills, install, preflight workflows；do not use for 假装依赖已经满足, 直接修改系统环境.
⭐ 0· 92·0 current·0 all-time
byvx：17605205782@52yuanchangxing
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description claim to perform preflight checks; declared requirement (python3), included README, spec, template, and a local Python script that scans a provided directory are all proportional and expected.
Instruction Scope
SKILL.md confines the skill to read-only environment checks and provides an alternative template-based output if execution isn't allowed. The included script reads files under the user-specified input directory and looks for headings, file lists, and pattern matches. This is appropriate for auditing a skill directory, but you should avoid passing system/root paths or other directories containing unrelated sensitive files because the script will read them for analysis.
Install Mechanism
No install spec (instruction-only skill). Script is Python-only and uses the standard library; no network downloads or package installs are performed by the bundle.
Credentials
No environment variables, credentials, or external service tokens are requested. The single binary requirement (python3) is minimal and appropriate for the provided script.
Persistence & Privilege
always is false and the skill does not request permanent presence or modify other skills. It may write an output file if you specify an output path (normal behavior) but does not change system configuration.
Assessment
This skill appears to do exactly what it says: run a read-only audit of a provided directory and produce a structured report. Before running: (1) confirm the --input path is the intended skill directory (do not point it at / or other system/private folders), (2) prefer --dry-run initially and review output on stdout rather than writing files to sensitive locations, (3) review the generated report for any masked secret snippets (the script searches for secret-like patterns and partially redacts them), and (4) if you cannot or do not want to run the Python script locally, the skill can produce text output from its templates without execution. Overall the bundle is coherent and low-risk given these precautions.Like a lobster shell, security has layers — review code before you run it.
latestvk972f2v5tzz0n5ykf2ze5hhb7s8384r5
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🧰 Clawdis
OSmacOS · Linux · Windows
Binspython3