Skills/PyPI/office-assistant-mcp

office-assistant-mcp@0.0.25

VERIFIED· install only

Publisher claims: "办公使用MCP工具" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher pypi · publishing for 723 daysInstalls 173Last detonated 24 h ago
$claude mcp add office-assistant-mcp -- uvx office-assistant-mcp
WatchReport an issue

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
AZURE_OPENAI_API_KEY_JPCOZE_TOKENConfiguration, not credentials: COZE_BOT_ID, DEPLOYMENT_NAME, ENDPOINT_URL, HEADLESS_MODE, PWDEBUG
Where it talks to
no vendor host named in the codeAlso yunjiglobal.com, coze.cn, azure.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 yunjiglobal.com, coze.cn, azure.com as well as its own vendor. The guard injects AZURE_OPENAI_API_KEY_JP, COZE_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx office-assistant-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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-13 and scored it 95/100 (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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)src/office_assistant_mcp/brand_list_lower.txt:5343 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)mλkiFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)src/office_assistant_mcp/brand_list_lower.txt:2504 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)ípsλFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈43 tok
1 file · 27 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for office-assistant-mcp@0.0.25 as of 23 h ago. This is the package itself, not its dependencies.