io.github.SepineTam/stata-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

  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

  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. source/agent_examples/langchain/main.py) — the recommended intake shape. PASS = no static red flag; static analysis cannot prove the code honors env-based secret handling at runtime.

• 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/stata_mcp/core/stata/stata_do/do.py: subprocess.* call with shell=True (command-injection prone); src/stata_mcp/core/data_info/base.py: outbound HTTP/socket call). discloses shell/exec capability: src/stata_mcp/core/stata/stata_do/do.py: subprocess.* call with shell=True (command-injection prone) discloses shell/exec capability: src/stata_mcp/utils/usable.py: subprocess.* call with shell=True (command-injection prone) discloses shell/exec capability: pyproject declares an exec-oriented dependency (pexpect/fabric/invoke) discloses dynamic code execution: src/stata_mcp/core/stata/builtin_tools/ado_install/base.py: uses eval()/exec() discloses dynamic code execution: src/stata_mcp/core/stata/stata_finder/macos.py: uses eval()/exec() 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 1.23.0 (patch bump): new capability primitive(s) in source: child_process, dynamic-eval, fs-write, http-client, subprocess; new hardcoded outbound host/BCC destination(s): api.deepseek.com, api.openai.com, docs.statamcp.com, github.com, haghish.github.io, pub-b55c5837ee41480ba0f902096dd9725d.r2.dev, r2.statamcp.com, sepinetam.github.io, smith.langchain.com, www.aidea-labs.com, www.statamcp.com.

• 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 tracking behavior — disclosure