docker-mcp@0.4.0
CAUTION· install onlyPublisher claims: "Enables an AI agent to run and inspect containers, build and pull images, manage volumes and networks, drive Compose projects, clean up, and run self-checking practice labs. Startup modes restrict it to read-only, labs-only, or full Docker control with confirmation before dangerous operations." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 4 of 4 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
- no credential variables read in the code
- Where it talks to
- no vendor host named in the codeAlso docker.com — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- no credential files read · no network
- What we could not test
- use of the skill by an agent
Connect it under the guard. Bundled scripts ran with no arguments; no agent task scenario for this bundle. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: HTTP URL with a raw public IP address. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
const out = await inside("wget -q -T 5 -O /dev/null http://1.1.1.1 2>/dev/null && echo reached || echo blocked");Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.install: { windows: "winget install Nothing", macos: "brew install nothing", linux: "sudo apt install nothing", url: "https://example.org" },Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.export const testConfig = (env: Record<string, string> = {}): Config => loadConfig({ ...env, CLAUDE_PLUGIN_DATA: env.CLAUDE_PLUGIN_DATA ?? "/tmp/docker-mcp-test" });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.const out = await inside("wget -q -T 5 -O /dev/null http://1.1.1.1 2>/dev/null && echo reached || echo blocked");Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.…mcp version` shows it, the extension in agent-extensions (docker-lab) pins it: `npx -y @falkenslab/[email protected]` in its `.mcp.json`, and its `plugin.json` require…Fix: Pin versions and sources; vendor anything fetched at install time.// it with `npx -y <package>@<version>` and never `npm install`. `--watch` rebuilds on change.Fix: Pin versions and sources; vendor anything fetched at install time.… title: "Check a lab", description: "Run the lab's check (its lab.json) in its running service: passed when it exits 0, with its output to explain what failed. For a teacher, whether a statement or a solution works;…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.Cost to the agent
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.
What would make this Verified
2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim falkenslab: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- HTTP URL with a raw public IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
- New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
- Privileged sudo command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- URL using a raw public IP address≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.