club.elron/public-rentals

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

  pass25% of grade

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

  Scanned 174 text field(s); no instruction-injection patterns found. PASS = no static red flag. A server can serve different tool descriptions at runtime (the rug-pull class), which static scanning cannot see.

• 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 "applications.get_status" has a secret-shaped input parameter "sessionToken" — secrets must never be tool parameters (the model would supply/handle the credential). tool "applications.update" has a secret-shaped input parameter "sessionToken" — secrets must never be tool parameters (the model would supply/handle the credential). tool "applications.create_document_upload" has a secret-shaped input parameter "sessionToken" — secrets must never be tool parameters (the model would supply/handle the credential). tool "applications.complete_document_upload" has a secret-shaped input parameter "sessionToken" — secrets must never be tool parameters (the model would supply/handle the credential). tool "applications.upload_document" has a secret-shaped input parameter "sessionToken" — secrets must never be tool parameters (the model would supply/handle the credential). tool "applications.submit" has a secret-shaped input parameter "sessionToken" — secrets must never be tool parameters (the model would supply/handle the credential). tool "viewings.get_status" has a secret-shaped input parameter "sessionToken" — secrets must never be tool parameters (the model would supply/handle the credential). tool "viewings.propose_availability" has a secret-shaped input parameter "sessionToken" — secrets must never be tool parameters (the model would supply/handle the credential). tool "viewings.respond_to_proposal" has a secret-shaped input parameter "sessionToken" — secrets must never be tool parameters (the model would supply/handle the credential). tool "quotes.create" has a secret-shaped input parameter "sessionToken" — secrets must never be tool parameters (the model would supply/handle the credential). tool "quotes.get" has a secret-shaped input parameter "sessionToken" — secrets must never be tool parameters (the model would supply/handle the credential). tool "quotes.accept" has a secret-shaped input parameter "sessionToken" — secrets must never be tool parameters (the model would supply/handle the credential). tool "reservations.get_status" has a secret-shaped input parameter "sessionToken" — secrets must never be tool parameters (the model would supply/handle the credential). tool "contracts.get_signing_link" has a secret-shaped input parameter "sessionToken" — secrets must never be tool parameters (the model would supply/handle the credential). tool "payments.get_status" has a secret-shaped input parameter "sessionToken" — secrets must never be tool parameters (the model would supply/handle the credential). tool "bookings.get_confirmation" has a secret-shaped input parameter "sessionToken" — 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

  unscannable10% of grade

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

  no prior version to diff (first sight of club.elron/[email protected]); version-drift / rug-pull cannot be evaluated. Cold-start risk is covered by point-in-time checks (injection_surface, supply_chain, credential_hygiene), not here.

• Transport config

  pass10% of grade

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

  remote endpoint "https://elron.club/api/agent/public/mcp" uses TLS (https); remote endpoint uses OAuth (strongest auth mode)