Security audit
Security checks for vulnerabilities and agentic risk
This skill is a local, read-only report helper with some documentation mismatch, but I found no evidence of hidden execution, exfiltration, persistence, or destructive behavior.
Install only if you want a Chinese-language local helper for reviewing an OpenClaw skill directory. Do not treat its output as a complete machine compatibility check, because it does not actually verify OS state, environment variables, sandbox conditions, or installed binaries beyond its own python3 requirement.
声明的核心用途是“安装前验证二进制、环境变量、配置、OS 与 sandbox 条件”，通常应体现对本机运行环境、依赖、平台约束或沙箱限制的检查。但这段代码完全没有检查二进制是否存在、环境变量、操作系统信息、sandbox 状态或安装可行性。相反，它通过读取 resources/spec.json 决定模式，执行的是通用文本/目录/CSV/模式扫描与 Skill 规范审计，并生成 Markdown/JSON 报告。因此其主要目的与声明明显不同。虽然代码没有做危险的系统修改，和‘不要直接修改系统环境’不冲突，但它缺失声明中的关键预检能力，同时具备多项未声明的审计/扫描能力，属于明显的描述与行为不一致。
The script dispatches into multiple generic auditing modes such as directory, CSV, pattern, and skill audits based on spec-controlled mode selection, which goes beyond a narrowly scoped install preflight checker. In a skill advertised as validating binaries, environment variables, OS, and sandbox suitability, this broad content-inspection/report-generation behavior creates capability drift and can be used to examine arbitrary local files and directories unrelated to installation safety.
L33-L35 的触发示例如“检查这台机器能不能装这个 skill”“说明缺哪些依赖”属于自然语言常见请求，缺少更明确的上下文约束、专用触发词或排除条件。文档虽然描述了用途，但没有说明何时不应触发该技能，可能与一般安装排障对话重叠。
The skill text explicitly contemplates shell execution via python3 .../scripts/run.py and references both reading local resources and producing output files, but it declares no permissions or allowed-tools scope. That mismatch can cause the runtime or a caller to grant broader capabilities than reviewers expect, weakening least-privilege and making unintended file or shell access easier.
The title, category label, and summary are written entirely in Chinese, which indicates a fixed language choice in user-facing skill metadata. The file does not mention any language selection, opt-in, or region-specific justification, so this appears to violate the requirement not to force a specific language or locale without user choice.
The helper enumerates arbitrary text files recursively under a user-supplied root and feeds them into later reporting functions. For a pre-install environment checker, unrestricted file and directory inspection is unnecessary and increases the chance of collecting unrelated sensitive information from the local workspace.
The report-generation functions emit user-facing headings and guidance exclusively in Chinese, such as "结果", "摘要", and workflow instructions. This enforces a specific language for generated output without offering the user a language choice or documenting a justified locale restriction, which matches the language/locale policy violation criteria.
The pattern scanning logic reads arbitrary file contents and searches for secrets, private URLs, and dangerous shell snippets, which is not justified by the declared install-check purpose. Even though it only reports matches, this expands the skill into a local content auditing tool that may expose sensitive data in output or encourage users to run it on broad paths.
The CLI presents itself as a local support script for the skill, but the accepted arguments and runtime behavior enable unrelated auditing/reporting workflows over arbitrary paths and inline input. This mismatch can mislead users into granting broader trust and running the tool in contexts where they would not expect local content inspection.
The file's natural-language instructions and headings are entirely in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the policy rule for language or locale constraints, this can be a natural-language policy violation when no opt-in or justification is provided.
The markdown file is entirely written in Chinese and presents a fixed example output format without any indication that users may choose another language or locale. Under the policy for natural-language violations, a skill can be problematic if it effectively enforces a specific language without opt-in or documented justification.
The markdown template uses Chinese in the title and instructional text, which implies the skill output is expected in a specific language. Under the policy criteria, forcing a language without user opt-in is a natural-language policy concern unless the locale restriction is explicitly justified.
No suspicious patterns detected.
