Skills/PyPI/sokgi-mcp

sokgi-mcp@0.2.3

VERIFIED· install only

Publisher claims: "Sokgi — read and write Korean business documents (HWP/HWPX/DOCX/XLSX/PPTX) from your AI agent" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher 14dimension-admin · publishing for 113 daysInstalls 47Last detonated 29 min ago
$claude mcp add sokgi-mcp -- uvx sokgi-mcp
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
3 of 3 bundled scripts run with no arguments, with decoy credentials in the environment · 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
SOKGI_API_KEYConfiguration, not credentials: SOKGI_API_URL, SOKGI_LOCAL_PARSE, SOKGI_STATE_FILE
Where it talks to
no vendor host named in the codeAlso 14dimension.com, evil.example — 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 14dimension.com, evil.example as well as its own vendor. The guard injects SOKGI_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx sokgi-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; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 93/100 (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 · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.0sprocessexited 1: ImportError: attempted relative import with no known parent package
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.2sprocessexited 1: ModuleNotFoundError: No module named 'mcp'
0.2sprocess3 of 3 bundled scripts run with no arguments
0.2sprocessscript backend runs setup only
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

No findings across 554 lines in 5 files.

Cost to the agent

Instructions loaded
≈58 tok
1 file · 5 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 sokgi-mcp@0.2.3 as of 4 min ago. This is the package itself, not its dependencies.