com.clinkforge/clink-forge

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 (api.clinkforge.com); capability text should not name where data goes.

• Supply chain

  warn25% of grade

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

  no resolvable repository linked to the package (provenance unverifiable)

• 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

  unscannable15% of grade

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

  No source files, package.json, or pyproject were fetched; cannot infer capability scope.

• Version behavior

  warn10% of grade

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

  vs prior 1.0.0 (patch bump): tool "spdx_license_lookup" description changed (wording only, no injection pattern); tool "usgs_quake_lookup" description changed (wording only, no injection pattern); tool "nws_alert_severity_summary" description changed (wording only, no injection pattern); tool "cpi_us_monthly" description changed (wording only, no injection pattern); tool "state_population_lookup" description changed (wording only, no injection pattern); tool "congress_bill_lookup" description changed (wording only, no injection pattern); tool "bank_profile_lite" description changed (wording only, no injection pattern); tool "fda_recall_lookup" description changed (wording only, no injection pattern); tool "fda_recall_state_summary" description changed (wording only, no injection pattern); tool "wb_country_lookup" description changed (wording only, no injection pattern); tool "aqi_site_lookup" description changed (wording only, no injection pattern); tool "aqi_category_summary" description changed (wording only, no injection pattern); tool "electricity_retail_series" description changed (wording only, no injection pattern); tool "state_gdp_series" description changed (wording only, no injection pattern); tool "fmr_area_lookup" description changed (wording only, no injection pattern); tool "fmr_area_search" description changed (wording only, no injection pattern); tool "station_monthly_temp" description changed (wording only, no injection pattern); tool "kev_status_by_cve" description changed (wording only, no injection pattern); tool "fedreg_doc_lookup" description changed (wording only, no injection pattern); tool "ecfr_title_status" description changed (wording only, no injection pattern); tool "us_debt_to_penny" description changed (wording only, no injection pattern); tool "cpsc_recall_monthly_summary" description changed (wording only, no injection pattern); tool "cpsc_recall_lookup" description changed (wording only, no injection pattern).

• 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)