pl.swiadectwo-energetyczne24/zamowienia

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

  fail25% of grade

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

  server instructions: instruction to hide activity from the user.

• 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

  fail15% of grade

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

  tool "get_certificate_order_requirements" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "update_certificate_order" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "get_certificate_order" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "get_certificate_order_status" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "calculate_certificate_price" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "get_payment_link" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "create_document_upload_url" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "add_property_document" has a secret-shaped input parameter "access_token" — secrets must never be tool parameters (the model would supply/handle the credential).

• 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 (minor bump): new tool "get_property_types" appeared; new tool "get_certificate_options" appeared; new tool "get_certificate_information" appeared; new tool "create_certificate_order" appeared; new tool "get_certificate_order_requirements" appeared; new tool "update_certificate_order" appeared; new tool "get_certificate_order" appeared; new tool "get_certificate_order_status" appeared; new tool "calculate_certificate_price" appeared; new tool "get_payment_link" appeared; new tool "create_document_upload_url" touches a sensitive surface (email/exec/net/fs); new tool "add_property_document" touches a sensitive surface (email/exec/net/fs).

• 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)