io.github.wrenchpilot/it-tools-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

  pass25% of grade

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

  Scanned 688 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

  fail25% of grade

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

  install hook "prepare" contains inline code eval; dependency "ping" is edit-distance 1 from popular package "pino" (typosquat candidate); dependency "ulid" is edit-distance 1 from top-20 package "uuid" (typosquat candidate); dependency "color" is edit-distance 1 from popular package "colors" (typosquat candidate); dependency "ps-list" is edit-distance 2 from popular package "eslint" (typosquat candidate)

• Credential hygiene

  fail15% of grade

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

  tool "decrypt_ansible_vault" has a secret-shaped input parameter "password" — secrets must never be tool parameters (the model would supply/handle the credential). tool "encrypt_ansible_vault" has a secret-shaped input parameter "password" — secrets must never be tool parameters (the model would supply/handle the credential). tool "generate_basic_auth" has a secret-shaped input parameter "password" — secrets must never be tool parameters (the model would supply/handle the credential). tool "generate_otp" has a secret-shaped input parameter "secret" — secrets must never be tool parameters (the model would supply/handle the credential). tool "hash_bcrypt" has a secret-shaped input parameter "password" — secrets must never be tool parameters (the model would supply/handle the credential). tool "scp" has a secret-shaped input parameter "privateKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "ssh" has a secret-shaped input parameter "privateKey" — secrets must never be tool parameters (the model would supply/handle the credential).

• Permission scope

  pass15% of grade

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

  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

  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 io.github.wrenchpilot/[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

  unscannable10% of grade

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

  local stdio server: no remote transport or auth surface, and no phone-home/telemetry signal found in source. Absence of transport findings is NOT a safety guarantee — phone-home hosts can be constructed at runtime and defeat static analysis.