mcp-security-audit

82 / 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

Audit MCP (Model Context Protocol) server configurations for security issues. Use this skill when: - Reviewing .mcp.json files for security risks - Checking MCP server args for hardcoded secrets or shell injection patterns - Validating that MCP package-runner dependencies use exact reviewed versions, not bare names, @latest, or ranges - Detecting mutable npm/npx, bunx, pnpm dlx, yarn dlx, npm exec, uvx, uv tool run, and pipx run references in MCP configurations - Auditing which MCP servers a pr…

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 4 places.

skills/mcp-security-audit/SKILL.md, line 284. Dangerous commands (eval, bash -c)?
skills/mcp-security-audit/SKILL.md, line 129(r'(?i)bash\s+-c\s', "bash -c execution"),
skills/mcp-security-audit/SKILL.md, line 130(r'(?i)sh\s+-c\s', "sh -c execution"),

Show 1 more

skills/mcp-security-audit/SKILL.md, line 365[HIGH] data-processor: Dangerous pattern in MCP server args: bash -c execution

Downloads and installs other software

The author does not mention this.

Found in 9 places.

skills/mcp-security-audit/SKILL.md, line 161PYTHON_RUNNERS = {"uvx", "uvx.exe", "uv", "uv.exe", "pipx", "pipx.exe"}
skills/mcp-security-audit/SKILL.md, line 275{ "command": "npx", "args": ["-y", "my-mcp-server@2.1.0"] }
skills/mcp-security-audit/SKILL.md, line 276{ "command": "uvx", "args": ["my-mcp-server@2.1.0"] }

Show 6 more

skills/mcp-security-audit/SKILL.md, line 277{ "command": "uvx", "args": ["--from", "my-mcp-server==2.1.0", "my-mcp-server"] }
skills/mcp-security-audit/SKILL.md, line 282{ "command": "npx", "args": ["-y", "my-mcp-server@latest"] }
skills/mcp-security-audit/SKILL.md, line 283{ "command": "npx", "args": ["-y", "my-mcp-server"] }
skills/mcp-security-audit/SKILL.md, line 284{ "command": "npx", "args": ["-y", "@scope/server@^2.1.0"] }
skills/mcp-security-audit/SKILL.md, line 285{ "command": "uvx", "args": ["my-mcp-server"] }
skills/mcp-security-audit/SKILL.md, line 289The extractor reviews every explicit `--package` / `-p` selector for JavaScript runners, and every `--from` (`uvx`, `uv tool run`) or `--spec` (`pipx run`) requ

Install

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

if [ -e ~/.agents/skills/'mcp-security-audit' ] || [ -L ~/.agents/skills/'mcp-security-audit' ]; then echo 'A skill folder named mcp-security-audit 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 "$d" checkout --quiet '227949a7542a55d2155c00e7cdb998d9a0fee4f3' -- 'skills/mcp-security-audit' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/mcp-security-audit' ~/.agents/skills/'mcp-security-audit' && 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-security-audit' ~/.claude/skills/'mcp-security-audit' (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`	82
2026-11-08	`797337f`	82
2026-11-07	`797337f`	82