io.github.activeing123/mcptoon

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

  unscannable25% of grade

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

  No tool descriptions, server instructions, prompts, or resources were fetched; nothing to scan for injection.

• Supply chain

  pass25% of grade

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

  Python build script has no build-time network/exec; repository linkage verified

• Credential hygiene

  warn15% of grade

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

  tests/test_router.py: embeds a PRIVATE KEY block. (in an example/sample file — lower severity, but a real key here still leaks.) Reads secrets from the environment (e.g. src/mcptoon/cache.py) — the recommended intake shape.

• Permission scope

  warn15% of grade

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

  has both shell/exec and network egress — capable of download-and-run, though no such path was observed (src/mcptoon/client.py: subprocess.* call; src/mcptoon/client.py: outbound HTTP/socket call). has both shell/exec and destructive filesystem writes (src/mcptoon/client.py: subprocess.* call; src/mcptoon/installer.py: destructive filesystem call (shutil.rmtree/os.remove/etc.)). discloses shell/exec capability: src/mcptoon/client.py: subprocess.* call discloses shell/exec capability: src/mcptoon/installer.py: subprocess.* call discloses broad/destructive filesystem access: src/mcptoon/installer.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: src/mcptoon/plugin.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) Capability DISCLOSURE, not a verdict: static analysis sees the primitive is present and reachable, not whether its use is attacker-controlled.

• 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 0.7.0 (patch bump): new capability primitive(s) in source: fs-write, http-client, subprocess; new hardcoded outbound host/BCC destination(s): 10.0.0.1, 127.0.0.1, agent-plugins.org, api.example.com, evil.com, example.com, github.com, json-schema.org, mcp.so, nodejs.org, pypi.org, registry.modelcontextprotocol.org, smithery.ai, user, www.apache.org, your-server.

• Transport config

  warn10% of grade

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

  manifest/source references usage stats behavior — disclosure