korean-tax-calc-mcp@0.68.0
CAUTION· not startedPublisher claims: "Korea (South Korea) tax calculator MCP server (142 tools) — corporate, income and VAT tax, non-resident withholding, foreign worker flat tax, branch and exit tax, transfer pricing, tax adjustments and statutory-form Excel, with statute citations. 한국 세금 계산·세무조정 MCP" 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
- no credential variables read in the code
- Where it talks to
- no vendor host named in the codeAlso go.kr — 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 under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
What changed since 0.57.1
vet-skills diff korean-tax-calc-mcp 0.57.1 0.68.0This version reaches for something 0.57.1 did not: 1 new host (go.kr). Compared from the two recorded runs, not from source.
- New hosts
- go.kr
0.57.1 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
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; Pipe-to-shell pattern. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
txt = subprocess.run(["pdftotext", "-layout", pdf, "-"], capture_output=True, text=True, check=True).stdout.splitlines()Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."LAW_OC${EQ}${V}" # 환경변수 줄 LAW_OC=<값>(.env·설정 예시)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.subprocess.run(["soffice", "--headless", "--calc", "--convert-to", "xlsx", "--outdir", str(out), path],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.curl -s "$URL" | python scripts/redact_oc.py > raw/law_xxx.json # 주소는 변수로만 — echo·set -x 금지Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.chmod +x "$hook"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.return eval(f, env)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.cp "$src" "$dir/check_no_oc_key.sh" && chmod +x "$dir/check_no_oc_key.sh"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.subprocess.run(["soffice", "--headless", "--calc", "--convert-to", "xlsx", "--outdir", str(out), path],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.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%- Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Unclaimed publisher≈ +8 on the totalClaim upstageai: 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.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
- Python exec or eval of computed code≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.