Is mcp-server-audit@1.0.0 safe to install?

mcp-server-audit@1.0.0

VERIFIED· install only

Publisher claims: "MCP Server 配置安全审计器。把本机各宿主(Claude Code / Codex / Cursor / Windsurf / 项目级 .mcp.json)的 MCP server 配置集中采集,对每个 server 确定性标记风险形态 (shell 包装执行 / 包管理器拉取远端代码 / 凭据写进 URL / 明文 HTTP / 环境变量暴露面 / 命令注入痕迹),再由 Agent 结合部署语境逐条做暴露面分析,输出分级清单与加固建议。审查的是「配置给了 Agent 什么能力」,不是 server 的代码质量。触发词: MCP 审计, MCP 安全, 检查 MCP 配置, MCP server 审查, mcp 配置体检, mcp 风险, mcp audit, mcp security review, check mcp servers, mcp config review, mcp server 检查, 审查工具权限。激活条件: 用户给出 MCP 配置语境(要求检查/审计 MCP server、配置文件路径, 或询问某个 MCP server 是否安全);与 MCP 无关的通用安全审查不触发。 NOT for: Skill 质量评审(用 skill-review-pro)、代码质量评审(用 code-review-ProMax)、交付覆盖审计(用 delivery-spec-audit)、server 代码漏洞挖掘(需要运行 server,本 skill 只读配置不执行任何 server)。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher z-zihan · publishing for 33 daysInstalls 98Last detonated 6d ago

$clawhub install mcp-server-audit

Watch Report an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.

Tested: every file read, file written and host contacted by what ran
Not tested: use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-08 and scored it 91/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations

t+CategoryObserved action

0.0sprocessno install scripts in bundle

0.0sprocessscript backend runs setup only

0.0sprocessno install scripts to re-run

Static findings

MEDIUM

npx invocation of non-well-known packageSKILL.md:193 · npx invocation of non-well-known package — may execute untrusted code- **P1 soon**: unversioned `npx -y`/`uvx`, plain HTTP, shell-wrapped commandFix: Pin versions and sources; vendor anything fetched at install time.

AST06

MEDIUM

npx invocation of non-well-known packageSKILL.md:87 · npx invocation of non-well-known package — may execute untrusted code- **P1 尽快**：`npx -y`/`uvx` 无版本 pin 的包运行器、明文 HTTP、shell 包装Fix: Pin versions and sources; vendor anything fetched at install time.

AST06

Cost to the agent

Instructions loaded

≈2,270 tok

1 file · 3 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.