SkillAudit report — modelcontextprotocol/python-sdk

Scanned 2026-04-30 by SkillAudit v0.3 (surface-tiered static checks + LLM-assisted prompt-injection red-team).

Commit: 3d7b311 · Stars: 22747 · Days since last push: 0

LLM prompt-injection probe: skipped — set ANTHROPIC_API_KEY to enable the LLM-assisted prompt-injection red-team

Overall grade: C (70/100)

Security findings

Production sources:

• HIGH src/mcp/cli/cli.py:48 — subprocess with shell=True — arguments are parsed by /bin/sh

subprocess.run([cmd, "--version"], check=True, capture_output=True, shell=True)

Test source (low-weight) — 3 total, deduct 5/0 per high/warn:

• WARN tests/shared/test_streamable_http.py:813 — HTTP client call with user-controlled argument 'mcp_url' (validation markers present but not verified against this call-site)

response = requests.post(

• WARN tests/shared/test_streamable_http.py:830 — HTTP client call with user-controlled argument 'mcp_url' (validation markers present but not verified against this call-site)

tools_response = requests.post(

• WARN tests/shared/test_streamable_http.py:848 — HTTP client call with user-controlled argument 'mcp_url' (validation markers present but not verified against this call-site)

response = requests.post(

Permissions

_No findings on this axis._

Credentials

Examples / samples (low-weight) — 1 total, deduct 5/0 per high/warn:

• WARN examples/clients/simple-chatbot/mcp_simple_chatbot/.env.example — .env file present in repo tree — verify it's a template, not real secrets

examples/clients/simple-chatbot/mcp_simple_chatbot/.env.example

Maintenance

Production sources:

• WARN (meta) — 442 open issues — triage backlog

442 open

Compatibility

_No findings on this axis._

Documentation

_No findings on this axis._

Methodology

SkillAudit v0.3 clones the repo at the provided ref (default: default branch, HEAD) into an ephemeral sandbox, runs six static checks over .js/.ts/.py sources, queries the GitHub API for maintenance signals, and runs an LLM-assisted prompt-injection red-team over the MCP tool surface. Each axis is scored against the published rubric — surface tiers, per-(axis, surface) caps, grade buckets, and worked examples are all documented there.

The v0.3 calibration update introduces surface tiering: every finding is tagged with the code path it lives in (production / installer / examples / benchmarks / scripts / test). Production findings deduct at full weight (-30 high, -10 warn); installer findings deduct at half (-15 / -5); examples, benchmarks, top-level scripts, and tests deduct at low weight (-5 / 0). This stops a chatty benchmarks/ or samples/ directory from dominating an otherwise-clean MCP server's grade.

The prompt-injection axis extracts each server.tool(...) / @app.tool registration + the first ~60 lines of handler body, hands them to Claude Haiku 4.5 with a red-team system prompt, and asks for structured findings on untrusted-content flow into tool responses. One API call per scan, bounded at ~15K input tokens.

How to improve this grade

• Security — static: validate tool-input URLs against an allowlist before fetch/axios calls; use execFile with argv arrays instead of exec with template strings; never pass untrusted strings to subprocess with shell=True.
• Security — prompt injection: never return fetched web-page / file / email content verbatim in a tool response. Wrap with a framing marker (e.g., <untrusted-content>...</untrusted-content>), summarize rather than inline, and never let untrusted content share a turn with credentials or other tool output.
• Credentials findings: redact env-var reads before log lines and error messages; treat any string that ends up in a tool response as public.
• Maintenance: if the repo is inactive, document the maintenance model — "MCP tool, no breaking changes expected" is a legitimate signal.
• Docs: add a README install + usage section with a copy-pasteable command; add a SECURITY.md with a disclosure channel.

_Report generated by skillaudit.dev_