io.github.JSONbored/metagraphed

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).

  tool "get_randomness_status" description: names an outbound copy/exfil destination (BCC/exfil verb). tool "get_tao_usd" description: bare 'IMPORTANT:' prose in a description (tag form is high-confidence; prose is warn). tool "get_chain_holders" description: bare 'IMPORTANT:' prose in a description (tag form is high-confidence; prose is warn). tool "get_subnet_holders" description: bare 'IMPORTANT:' prose in a description (tag form is high-confidence; prose is warn).

• Supply chain

  warn25% of grade

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

  dependency "@posthog/core" is edit-distance 1 from popular package "cors" (typosquat candidate); dependency "graphql-ws" is edit-distance 2 from popular package "graphql" (typosquat candidate); dependency "yaml" is edit-distance 2 from popular package "yarn" (typosquat candidate)

• Credential hygiene

  fail15% of grade

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

  tool "get_alert_trigger" has a secret-shaped input parameter "owner_token" — secrets must never be tool parameters (the model would supply/handle the credential). tool "call_subnet_surface" has a secret-shaped input parameter "credential" — secrets must never be tool parameters (the model would supply/handle the credential). tool "write_subnet_surface" has a secret-shaped input parameter "credential" — secrets must never be tool parameters (the model would supply/handle the credential). tool "store_surface_credential" has a secret-shaped input parameter "credential" — 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.JSONbored/[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

  warn10% of grade

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

  sends telemetry to third-party SDK (posthog) — disclosure, verify opt-in