mcp-implementation-security-review

94 / 100 · Low risk

Fine to try. Some of what it can do is expected: a security skill usually runs scanners and checks websites.

By github/awesome-copilot (GitHub) · security · 41,001 stars · scanned at commit 227949a

Review the implementation source code of MCP (Model Context Protocol) servers, clients, and tool handlers against a security baseline — authentication, sessions, rate limiting, input-schema validation, official-SDK usage, RCE vectors, and the OWASP MCP Top 10 — producing a report with file/line evidence. Use this skill when: - Reviewing an MCP server implementation for security before release - Checking a server against the baseline controls (MCP-01 to MCP-05) and the OWASP MCP Top 10 - Auditin…

Works with any agent that supports SKILL.md skills.

What this skill can do

Runs commands on your computer

This is disclosed by the author in the skill's SKILL.md or README. Expected for a security skill.

Found in 3 places.

skills/mcp-implementation-security-review/SKILL.md, line 216| Command injection | `exec("convert " + args.filename)`, `os.system(f"process {user_input}")`, `Process.Start("cmd", "/c " + toolArg)` | `execFile("convert", [
skills/mcp-implementation-security-review/SKILL.md, line 217| Dynamic code evaluation | `eval(args.expression)`, `exec(tool_output)`, `new Function(args.code)()` | Sandboxed parser, AST-based evaluation, or predefined al
skills/mcp-implementation-security-review/SKILL.md, line 244Pass: No shell execution from untrusted input, or only parameterized allowlisted execution. Fail: User input reaches shell commands, `shell=True` with formatted

Connects to the internet

This is disclosed by the author in the skill's SKILL.md or README. Expected for a security skill.

Found in 1 place.

skills/mcp-implementation-security-review/SKILL.md, line 222| SSRF | `requests.get(user_param)`, `fetch(user_input)`, `HttpClient.GetAsync(user_input)` | Allowlist schemes/domains, block RFC1918 and link-local targets, v

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'mcp-implementation-security-review' ] || [ -L ~/.agents/skills/'mcp-implementation-security-review' ]; then echo 'A skill folder named mcp-implementation-security-review already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/github/awesome-copilot' "$d" && git -C "$d" checkout --quiet '227949a7542a55d2155c00e7cdb998d9a0fee4f3' -- 'skills/mcp-implementation-security-review' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/mcp-implementation-security-review' ~/.agents/skills/'mcp-implementation-security-review' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'mcp-implementation-security-review' ~/.claude/skills/'mcp-implementation-security-review' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for github/awesome-copilot shows the score of its lowest-scoring skill.

SkillTrust badge for github/awesome-copilot

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/github/awesome-copilot.svg)](https://zalavijaysinh.github.io/skilltrust/repos/github/awesome-copilot/)

Score history

Date	Version	Score
2026-11-10	`227949a`	94
2026-11-08	`797337f`	94
2026-11-07	`797337f`	94