io.github.kishida-devil/jp-payroll-mcp

What we checked

Six static checks, weighted by risk. Every result reflects only what could be observed in the published package and repository — never intent.

• Injection surface

  warn25% of grade

  Tool descriptions/manifest scanned for instruction-injection patterns (imperatives at the model, hidden text, 'ignore previous', data-exfil URLs).

  server instructions: off-vendor URL in a description (japan-payroll-api.tsumugi.workers.dev); capability text should not name where data goes. server instructions: off-vendor URL in a description (rapidapi.com); capability text should not name where data goes.

• Supply chain

  pass25% of grade

  Package provenance: namespace verification, repo linkage, maintainer count, account age, postinstall scripts, typosquat distance.

  repository linkage verified

• Credential hygiene

  pass15% of grade

  How the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.

  No hardcoded secrets, secret-shaped tool parameters, or leaked keys found. PASS = no static red flag; static analysis cannot prove the code honors env-based secret handling at runtime.

• Permission scope

  pass15% of grade

  Declared tools vs. breadth (filesystem, network, exec); flags shell-exec and unbounded filesystem access.

  Network egress present (src/index.mjs: outbound HTTP/socket call) — expected for most servers and not a finding on its own. No shell-exec, unbounded/sensitive filesystem, or download-and-run primitives found in scanned source. PASS = no static red flag. Static scanning is blind to code fetched or executed at runtime.

• Version behavior

  fail10% of grade

  Diff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).

  vs prior 0.4.3 (patch bump): new tool "calculate_payslip" appeared; new tool "list_workers_compensation_rates" touches a sensitive surface (email/exec/net/fs); new tool "calculate_bonus" appeared; new tool "calculate_withholding_tax" appeared; new tool "judge_monthly_revision" appeared; new tool "decide_regular_remuneration" appeared; new tool "judge_leave_end_revision" touches a sensitive surface (email/exec/net/fs); new tool "calculate_payroll_batch" touches a sensitive surface (email/exec/net/fs); new tool "decide_regular_remuneration_batch" touches a sensitive surface (email/exec/net/fs); new tool "judge_annual_average" appeared; new tool "lookup_standard_remuneration" appeared; new tool "national_insurance" appeared; new tool "calculate_annual_cost" appeared; new tool "judge_annual_leave" appeared; new tool "judge_worker_type" touches a sensitive surface (email/exec/net/fs); new tool "check_insurance_eligibility" appeared; new tool "check_leave_exemption" appeared; new tool "get_age_milestones" appeared; new tool "calculate_year_end_adjustment" appeared; new tool "estimate_resident_tax" appeared; new tool "get_insurance_rates" appeared; new tool "get_minimum_wage" appeared; new tool "business_days" appeared; new tool "validate_invoice_numbers_batch" whose description contains do-not-tell-the-user phrase; new tool "validate_corporate_number" appeared; new tool "consumption_tax" appeared; new tool "get_statute_text" touches a sensitive surface (email/exec/net/fs); new tool "calculate_overtime_pay" appeared; new tool "commuting_allowance_exemption" touches a sensitive surface (email/exec/net/fs); new tool "check_data_freshness" appeared; new capability primitive(s) in source: http-client; new hardcoded outbound host/BCC destination(s): github.com, host, japan-payroll-api.tsumugi.workers.dev, japan-payroll-api.tsumugi.workers.dev., rapidapi.com, www.npmjs.com.

• Transport config

  fail10% of grade

  Remote servers: TLS and auth mode (none/token/OAuth). Local servers: whether the manifest indicates it phones home.

  remote MCP endpoint declares NO authentication (unauthenticated remote — nginx-ui/CVE-2026-33032 class); manifest/source references analytics behavior — disclosure