verified-googledocs-mcp@0.2.0
CAUTION· not startedPublisher claims: "MCP server for Google Docs with verified writes" 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
VERIFIED_GOOGLEDOCS_MCP_CREDENTIALSConfiguration, not credentials: XDG_STATE_HOME- Where it talks to
- no vendor host named in the codeAlso google.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
- 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 google.com as well as its own vendor. The guard injects VERIFIED_GOOGLEDOCS_MCP_CREDENTIALS 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 2026-11-20 and scored it 76/100 (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; Access to sensitive file paths; Hidden zero-width characters detected. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
# ~/.ssh, ~/.aws, etc. to a doc-driven diff.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.".netrc",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.the file is written atomically (temp file chmod 0o600, then renamed) so itFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts."Soft hyphen: superseded\n"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.s = s.replace(" ", " ").replace("", "") # NBSP -> space, soft hyphen -> goneFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.if ch == "":Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.assert "👨👩👧" in afterFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.# = NBSP, = soft hyphen. The duplicated fox sentence must appearFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.# Open append-only, creating with owner-only perms; chmod each time so aFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts."content": "Soft hyphen: superseded\n",Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."ZWJ emoji sequence: \U0001f468\U0001f469\U0001f467 "Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.(which technically contains ~/.ssh), diff_tab_vs_file must refuse toFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# 👨💻 is U+1F468 ZWJ U+1F4BB = 2 + 1 (ZWJ is BMP) + 2 = 5 UTF-16 units.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.tab = _tab(["programming"])Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.".netrc",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.tab = _tab(["programming"])Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.seq = "👨👩👧"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.("softhyphen", "softhyphen"), # soft hyphen strippedFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.denylist exists for ("diff against ~/.ssh/id_rsa")."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# On macOS, Path.home() reads /etc/passwd, not $HOME, so patch it directly.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.denylist exists for ("diff against ~/.ssh/id_rsa")."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# 👨👩👧 is a ZWJ sequence: three emoji + two ZWJs = 3*2 + 2*1 = 8 UTF-16 units.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent."content": "ZWJ emoji sequence: 👨👩👧 (family: man+ZWJ+woman+ZWJ+girl)\n",Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.zwj_seq = "\U0001f468\U0001f4bb"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.runpy.run_module("verified_googledocs_mcp", run_name="__main__")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = locate("programming", tab)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.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
Not checked against OSV yet; the weekly check has not reached this version.
What would make this Verified
4 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim michaelrobertsutton: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- 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.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- References a credential file in the home directory≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Dynamic module loading≈ +1 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.