com.opedd/opedd-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

  warn25% of grade

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

  server instructions: off-vendor URL in a description (opedd.com); capability text should not name where data goes. server instructions: off-vendor URL in a description (opedd.com,); capability text should not name where data goes. server instructions: off-vendor URL in a description (mcp.opedd.com); capability text should not name where data goes.

• Supply chain

  pass25% of grade

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

  repository linkage verified

• Credential hygiene

  fail15% of grade

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

  tool "get_content" has a secret-shaped input parameter "buyer_token" — 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

  fail10% of grade

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

  vs prior 0.6.8 (patch bump): tool "get_audit_events" description changed (wording only, no injection pattern); tool "get_buyer_account" description changed (wording only, no injection pattern); tool "article_53_attestation" description changed (wording only, no injection pattern); tool "get_compliance_dossier" description changed (wording only, no injection pattern); tool "push_content" description changed (wording only, no injection pattern); new hardcoded outbound host/BCC destination(s): github.com, opedd.com.

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