Skills/npm/cloud-run-mcp

cloud-run-mcp@1.12.0

CAUTION

Publisher claims: "Cloud Run MCP deployment tool" Observed in sandbox: sends data to metadata.google.internal, 169.254.169.254, metadata.google.internal..

Registry npm (MCP server)Publisher google-cloud · publishing for 459 daysInstalls 35,845Last detonated 4d ago
What would fix thisWatchDispute verdict

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

Before you give it your token

It will ask for
GOOGLE_OAUTH_AUDIENCEGOOGLE_OAUTH_CLIENT_IDGOOGLE_OAUTH_CLIENT_SECRETGOOGLE_OAUTH_REDIRECT_URIOAUTH_AUTHORIZATION_ENDPOINTOAUTH_AUTHORIZATION_SERVEROAUTH_ENABLEDOAUTH_PROTECTED_RESOURCEOAUTH_TOKEN_ENDPOINTConfiguration, not credentials: ALLOWED_HOSTS, AR_DOWNLOAD_PATH_PREFIX, DEFAULT_SERVICE_NAME, ENABLE_HOST_VALIDATION, GCP_STDIO, GOOGLE_CLOUD_PROJECT, GOOGLE_CLOUD_REGION, NAME, RUN_INGRESS_POLICY, SKIP_IAM_CHECK
Where it talks to
no vendor host named in the codeAlso google.com, google.internal — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · contacted metadata.google.internal, 169.254.169.254, metadata.google.internal. (undeclared)
What we could not test
what the tools do when called with real credentials

Find out what these hosts are first. In the honeypot it contacted metadata.google.internal, 169.254.169.254, metadata.google.internal., which nothing in the package names as its own. If that is the vendor's service, fine; if you cannot place it, do not connect it.

$vet-skills run --net metadata.google.internal,169.254.169.254,metadata.google.internal. -- npx -y @google-cloud/cloud-run-mcp

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) on 2026-11-11 and scored it 65/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths. Summary: sends data to metadata.google.internal, 169.254.169.254, metadata.google.internal..

Behavior trace

Honeypot run · 45 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
25sprocessdependency install exit 0
45snetworkCONNECT tcp://metadata.google.internal:80 · not in the allow-list, refused
45snetworkCONNECT tcp://169.254.169.254:80 · not in the allow-list, refused
45snetworkCONNECT tcp://metadata.google.internal.:80 · not in the allow-list, refused
45snetworkCONNECT tcp://metadata.google.internal:80 · not in the allow-list, refused
45sclaimed8 tools: list_projects, create_project, list_services, get_service, get_service_log, deploy_local_folder, deploy_file_contents, deploy_container_image
45sprocessscript backend runs setup only
45sprocessno install scripts to re-run

Static findings

MEDIUM
Destructive file system command detectedexample-sources-to-deploy/golang/Dockerfile:43 · Destructive file system command detectedrm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actiontest/need-gcp/test-helpers.js:171 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('Adding editor role to Compute SA...');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsmcp-server.js:41 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files//Suppress the warning related to missing .env file in case of non-OAuth modeFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actiontest/need-gcp/test-helpers.js:178 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('Compute SA editor role added.');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈1,294 tok
2 files · 80 in bundle
Tool list per prompt
≈1,141 tok
8 tools · 143 per tool
Handshake
1074 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 104

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 @google-cloud/cloud-run-mcp@1.12.0 as of 4d ago. This is the package itself, not its dependencies.

What would make this Verified

15 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
  2. Unclaimed publisher≈ +8 on the totalClaim google-cloud: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim google-cloudPropose a patch to the maintainer