← 返回 Skills 市场
798
总下载
0
收藏
1
当前安装
2
版本数
在 OpenClaw 中安装
/install validator-agent
功能描述
Validates project pre-deployment by running comprehensive security, testing, quality, documentation, CI/CD, privacy, maintainability, usability, marketabilit...
安全使用建议
This skill appears to do the validation tasks it describes, but it will execute project-provided scripts (npm test, npm run lint, forge commands, etc.) which can run arbitrary code from the repository. Before installing or running it: 1) only run the skill on projects you trust or inside an isolated environment (container, VM, CI runner with restricted permissions); 2) ensure the agent environment has the expected tools (node/npm/npx, forge, slither, type-coverage) or the skill may fail; 3) be aware it writes reports to ops/reports/, despite claiming to be 'read-only'; 4) prefer running this on CI or sandboxed machines rather than on a developer workstation with access to secrets; 5) note the package metadata and registry metadata mismatch and the skill has no published source/homepage — consider asking the publisher for provenance before use.
功能分析
Type: OpenClaw Skill
Name: validator-agent
Version: 1.1.0
The skill is highly suspicious due to critical shell injection vulnerabilities. The `<project>` placeholder, which is user-controlled input, is directly concatenated into multiple `cd <project> && ...` shell commands within SKILL.md (e.g., Round 0, Round 1, Round 2, Round 3, Round 4). This allows an attacker to inject arbitrary shell commands, leading to Remote Code Execution (RCE). Additionally, the report saving path `ops/reports/validator-YYYY-MM-DD-HH-[project].md` uses the unsanitized `<project>` input, creating a path traversal vulnerability that could allow writing the report to arbitrary file system locations.
能力评估
Purpose & Capability
The SKILL.md behavior (TypeScript and Solidity validation: tsc/forge, npm audit, tests, lint, type-coverage, docs/changelog checks) aligns with the skill name and description. However the skill does not declare the many runtime tools it actually expects (node/npm/npx, forge, slither, type-coverage, tail) — the packaged metadata lists only a generic 'exec' requirement. This mismatch means the agent environment may lack required binaries or the operator may be surprised by tools the skill will invoke.
Instruction Scope
The instructions tell the agent to cd into project folders and run project-provided commands (npm test, npm run lint, npx tsc, forge build/test, npm audit, npx type-coverage). Running those commands executes code and scripts from the target repository (package.json scripts, test/setup code, etc.), which can run arbitrary commands with the agent's privileges. The skill also reads workspace-level files (ops/test-baselines.md, package.json, README.md, CHANGELOG.md) and writes reports to ops/reports/..., so although the SKILL.md claims 'read-only', it writes output into the workspace. There are no instructions to limit or sandbox script execution.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, which minimizes install-time risk. There is no URL download or package install performed by the skill bundle itself.
Credentials
The skill declares no required environment variables or credentials, which is consistent with its stated checks. However it implicitly requires various binaries and tools (node/npm/npx, forge, slither, type-coverage, tail) that are not declared as required. That omission reduces transparency about the privileges and capabilities the skill will use at runtime.
Persistence & Privilege
The skill is not always-enabled and uses normal autonomous invocation settings. It does not request persistent system configuration changes in its files. The only notable behavior is saving reports into ops/reports/, which is normal for a reporting tool but contradicts the SKILL.md's 'read-only' claim about not modifying code.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install validator-agent - 安装完成后，直接呼叫该 Skill 的名称或使用
/validator-agent触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.1.0
Validator Agent 1.1.0 — concise pipeline, 8-entry checklist, and TypeScript/Solidity focus
- Overhauled documentation: now describes a focused 8-round validation pipeline (compile, lint, test, security, type coverage, docs, changelog, final summary)
- Skill narrowed to TypeScript/Solidity; project detection clarified via `package.json` and `foundry.toml`
- Removed extensive/complex checklist and broad language support; simplified for clarity and reliability
- Dropped README.md in favor of documentation in SKILL.md
- Improved output and review flow: produces a `validator-YYYY-MM-DD-HH-[project].md` report with clear pass/block decision
- Makes clear this skill never auto-publishes, only reports and recommends
v1.0.0
Initial release: 10-section pre-deployment quality gate for OpenClaw skills
元数据
常见问题
Validator Agent 是什么？
Validates project pre-deployment by running comprehensive security, testing, quality, documentation, CI/CD, privacy, maintainability, usability, marketabilit... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 798 次。
如何安装 Validator Agent？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install validator-agent」即可一键安装，无需额外配置。
Validator Agent 是免费的吗？
是的，Validator Agent 完全免费（开源免费），可自由下载、安装和使用。
Validator Agent 支持哪些平台？
Validator Agent 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Validator Agent？
由 up2itnow（@up2itnow）开发并维护，当前版本 v1.1.0。
推荐 Skills