ai.uselamina/lamina

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).

  tool "lamina_describe" description: off-vendor URL in a description (...); 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

  fail15% of grade

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

  tool "lamina_discover" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_describe" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_run" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_status" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_models_list" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_models_describe" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_generate_image" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_generate_video" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_brand" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_upload_asset" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_cancel" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_create" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_generate_workflow" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_app_versions" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_set_visibility" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_set_brand" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_brand_feedback" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_brand_compliance" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_brand_score" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_refine_to_brand" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_credits" has a secret-shaped input parameter "apiKey" — secrets must never be tool parameters (the model would supply/handle the credential). tool "lamina_topup" has a secret-shaped input parameter "apiKey" — 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 ai.uselamina/[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://app.uselamina.ai/mcp/agent" uses TLS (https); remote endpoint uses OAuth (strongest auth mode)