io.github.CSOAI-ORG/gspc

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 "board_totals" description: off-vendor URL in a description (councilof.ai); capability text should not name where data goes. tool "get_axis" description: off-vendor URL in a description (councilof.ai); capability text should not name where data goes. tool "verify_card" description: off-vendor URL in a description (councilof.ai); capability text should not name where data goes. tool "list_cards" description: off-vendor URL in a description (councilof.ai); capability text should not name where data goes. tool "get_root" description: off-vendor URL in a description (councilof.ai); capability text should not name where data goes. tool "get_card" description: off-vendor URL in a description (councilof.ai); capability text should not name where data goes. tool "commission_card" description: off-vendor URL in a description (councilof.ai); capability text should not name where data goes. tool "art50_marking_evidence" description: off-vendor URL in a description (councilof.ai); capability text should not name where data goes. tool "rwa_evidence" description: off-vendor URL in a description (councilof.ai); capability text should not name where data goes. tool "rwa_evidence" param "asset" description: off-vendor URL in a description (councilof.ai); capability text should not name where data goes. tool "witness_hash" description: off-vendor URL in a description (councilof.ai); capability text should not name where data goes. tool "receipts_batch" description: off-vendor URL in a description (councilof.ai); capability text should not name where data goes. server instructions: off-vendor URL in a description (councilof.ai); 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

  pass15% of grade

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

  Reads secrets from the environment (e.g. index.mjs) — the recommended intake shape. PASS = no static red flag; static analysis cannot prove the code honors env-based secret handling at runtime.

• Permission scope

  pass15% of grade

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

  Network egress present (index.mjs: outbound HTTP/socket call) — expected for most servers and not a finding on its own. 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 1.1.1 (minor bump): new tool "commission_card" whose description contains embedded outbound URL; new tool "art50_marking_evidence" whose description contains embedded outbound URL; new tool "rwa_evidence" whose description contains embedded outbound URL; new tool "witness_hash" whose description contains embedded outbound URL; new tool "receipts_batch" whose description contains embedded outbound URL; new capability primitive(s) in source: http-client; new hardcoded outbound host/BCC destination(s): councilof.ai, csoai.org, github.com, www.csoai.org.

• 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)