io.github.anish632/ground-truth

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 "check_pricing" param "url" description: off-vendor URL in a description (stripe.com); 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

  pass15% of grade

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

  No hardcoded secrets, secret-shaped tool parameters, or leaked keys found. PASS = no static red flag; static analysis cannot prove the code honors env-based secret handling at runtime.

• 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

  pass10% of grade

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

  vs prior 0.5.3 (minor bump): tool "create_monitor" description changed (wording only, no injection pattern); tool "list_monitors" description changed (wording only, no injection pattern); tool "run_monitor_now" description changed (wording only, no injection pattern); tool "get_monitor_result" description changed (wording only, no injection pattern); tool "delete_monitor" description changed (wording only, no injection pattern); tool "generate_change_report" description changed (wording only, no injection pattern); tool "create_share_link" description changed (wording only, no injection pattern); new tool "preview_monitor" appeared. Low-severity drift (informational; consistent with the version bump).

• 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)