mcp-warden-cli@2.2.0
CAUTION· not startedPublisher claims: "CI-first MCP supply-chain integrity gate: pin and verify the declared tool/resource/prompt surface of an MCP server, plus runtime tool-result inspection (guard/inspect)." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
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
ACTIONS_ID_TOKEN_REQUEST_TOKENACTIONS_ID_TOKEN_REQUEST_URLAPI_KEYor--identity-token/--block-secret-echo/--no-block-secret-echo/--redact-secret-echoConfiguration, not credentials: GITHUB_REF, WARDEN_ACTOR, WARDEN_APPROVER, WARDEN_ENV, WARDEN_LOG_LEVEL, WARDEN_PYPI_PUBLISHER_CONFIRMED- Where it talks to
- no vendor host named in the codeAlso githubusercontent.com, schemastore.org — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names githubusercontent.com, schemastore.org as well as its own vendor. The guard injects ACTIONS_ID_TOKEN_REQUEST_TOKEN, ACTIONS_ID_TOKEN_REQUEST_URL, API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.
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; not started: dependency install failed; the server itself was not observed) on 2026-11-10 and scored it 73/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Pipe-to-shell pattern; URL with embedded credentials. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
"""Detect a ``curl ... | sh`` / ``wget ... | sh`` remote-fetch-execute shape."""Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.``node ./server.js``, an unpinned ``npx pkg``, ``--url`` with no coordinate —Fix: Pin versions and sources; vendor anything fetched at install time.out = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.``https://user:tok@host/path`` -> ``https://host`` — the audit must not widenFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."-- any uncompleted inspection ends the session (a false-positive kill is the "Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# Windows Job Object limit flag: kill all processes in the job when the last jobFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.out = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."Launch reconstructs a remote-fetch-execute (curl|sh / wget|sh) shape",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."""Detect a ``curl ... | sh`` / ``wget ... | sh`` remote-fetch-execute shape."""Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.add("WRD-SUP-NPX-UNPINNED", "high", "Unpinned npx package (resolves latest at run)", spec)Fix: Pin versions and sources; vendor anything fetched at install time.# curl|sh shape first (critical), independent of package managers.Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.add("WRD-SUP-LATEST-TAG", "high", "Explicit floating 'latest' tag in npx spec", spec)Fix: Pin versions and sources; vendor anything fetched at install time.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for mcp-warden-cli@2.2.0 as of 4d ago. This is the package itself, not its dependencies.
What would make this Verified
7 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Unclaimed publisher≈ +8 on the totalClaim datascience-engineeringexperts: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- URL with embedded credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.