sandbase-harness
Local-first AI agent runtime with sandboxed sessions, MCP tools, memory, credentials, audit/replay, and a built-in console. Run OpenAI, Anthropic, MiniMax, DeepSeek V4, and OpenAI-compatible models on your infrastructure.
Warning. Serious findings were identified. Review the full report before connecting. 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
sandbaseai
Source: github_topic
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
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
When Vitest UI server is listening, arbitrary file can be read and executed
nanoid: non-secure generators can loop indefinitely with negative size
nanoid: custom generators can loop indefinitely when size is zero
vite: `server.fs.deny` bypass on Windows alternate paths
Vite Vulnerable to Path Traversal in Optimized Deps `.map` Handling
MANAGED_AGENTS_API_KEYFor an authenticated remote runtime, also pass . TheMANAGED_AGENTS_CORS_ORIGINSMANAGED_AGENTS_ENVIRONMENT_KEYMANAGED_AGENTS_HOMEMANAGED_AGENTS_LOG_FORMATMANAGED_AGENTS_LOG_LEVELMANAGED_AGENTS_SECRET_KEYMANAGED_AGENTS_URLexport =http://127.0.0.1:3000Tool 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
6/6 tools missing one or more hints — list_agents (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); create_session (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); run_session (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +3 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.
Tool inputs are validated
5/6 tool handlers declare input schemas (83%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool test coverage
Only 0/6 tools referenced in tests (0%)
Write tests that reference each tool by name so every tool has at least one test.
Shell command execution
18 child_process/subprocess calls in production code — runs shell commands (src/cli/worker-commands.ts:100, src/sandbox/docker-provider.ts:32, src/sandbox/docker-provider.ts:78)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Secrets stay with their owner
1 secret/sensitive value flow into network calls (MANAGED_AGENTS_ENVIRONMENT_KEY → dynamic)
Audit where credentials are sent. A NOTION_TOKEN should only reach api.notion.com — never a third-party host.
Secrets never reach shell commands
1 secret value passed to shell commands — possible command injection
Never pass secrets through shell commands. Use library APIs that accept credentials as arguments.
Production dependencies are patched
0 critical, 2 high severity in production deps — nanoid@3.3.15 (high), nanoid@3.3.15 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
2 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
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/sandbaseai-sandbase-harness-wfy0es)?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