ai-workbench
本地优先的桌面 AI 工作台：目标驱动、多 Agent 并行、百万 Token 上下文、Office 处理、深度研究、网站部署、插件生态、多节点集群、提示词工程与企业级安全审计
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
wxz1gh46
Source: github_repo_search
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
fs.read读取工作区内文本文件内容
fs.write写入文本文件（自动创建目录）
fs.list列出目录内容
office.generate生成 docx / xlsx / pptx / pdf / markdown 文件并写入工作区
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@hono/node-server has authorization bypass for protected static paths via encoded slashes in Serve Static Middleware
Drizzle ORM has SQL injection via improperly escaped SQL identifiers
Hono JWK Auth Middleware has JWT algorithm confusion when JWK lacks "alg" (untrusted header.alg fallback)
hono: CORS Middleware reflects any Origin with credentials when `origin` defaults to the wildcard
Hono JWT Middleware's JWT Algorithm Confusion via Unsafe Default (HS256) Allows Token Forgery and Auth Bypass
CLOUDFLARE_ACCOUNT_IDCLOUDFLARE_PROJECTDB_FILELOCAL_PREVIEW_ROOTNETLIFY_SITE_IDPGSSL_NOSTRICTPG_STATEMENT_TIMEOUTWORKBENCH_TOKEN_BUDGET_USDTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
4/4 tools missing one or more hints — fs.read (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); fs.write (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); fs.list (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +1 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Production dependencies are patched
0 critical, 14 high severity in production deps — @hono/node-server@1.13.7 (high), drizzle-orm@0.36.4 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dependency freshness
1/15 production deps stale: pdf-lib@2022-05-12 (4.3y)
Domain consistency
npm scope @ai doesn't match GitHub owner wxz1gh46
Use the same org name across GitHub, npm, and your homepage so users can verify the publisher.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/wxz1gh46/ai-workbench)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check