gmail-mcp@0.3.0
VERIFIED· install onlyPublisher claims: "Connects Gmail to Claude and other MCP clients so users can search and read mail, send and reply-all with quoted history, forward messages, handle attachments and inline images, and manage drafts, labels, and threads across multiple Google accounts simultaneously from a self-hosted remote server." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- 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: Verified 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
GOOGLE_CLIENT_SECRETOAUTH_KVOAUTH_PROVIDERConfiguration, not credentials: ALLOWED_EMAILS, COOKIE_ENCRYPTION_KEY, GOOGLE_CLIENT_ID, MAX_ACCOUNTS, MCP_OBJECT, RATE_LIMITER, REGISTER_LIMITER- Where it talks to
- no vendor host named in the codeAlso google.com — 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
- use of the skill by an agent
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names google.com as well as its own vendor. The guard injects GOOGLE_CLIENT_SECRET, OAUTH_KV, OAUTH_PROVIDER 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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-14 and scored it 85/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.html = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.expect(mime).toContain("filename*=UTF-8''%E5%A0%B1%E5%91%8A%E6%9B%B8.docx");Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.console.log("\n Could not read the namespace id from wrangler's output.");Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.expect(raw).toContain("filename*=UTF-8''%E8%AB%8B%E6%B1%82%E6%9B%B8");Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.console.log(` Put it in ${LOCAL} under kv_namespaces, then re-run.\n`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.["file", "file:///etc/passwd"],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.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.