← All skills

Snyk Agent Scan

100 / 100 · Low risk

Fine to try.

By skillmds/skillmd (GitHub) · coding · 143 stars · scanned at commit 4467dd0

Scan your AI agents, MCP servers, and skills for security vulnerabilities from the command line. Snyk Agent Scan discovers and audits every agent component on your machine — detecting prompt injections, tool poisoning, toxic flows, malware payloads, and credential handling issues across 15+ distinct risk categories.

Works with any agent that supports SKILL.md skills.

What this skill can do

We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.

Install

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

if [ -e ~/.agents/skills/'snyk-agent-scan' ] || [ -L ~/.agents/skills/'snyk-agent-scan' ]; then echo 'A skill folder named snyk-agent-scan already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/skillmds/skillmd' "$d" && git -C "$d" checkout --quiet '4467dd0debe8f189ba78142ee57ec42aea84e623' -- 'plugins/security/skills/snyk-agent-scan' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/security/skills/snyk-agent-scan' ~/.agents/skills/'snyk-agent-scan' && 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/'snyk-agent-scan' ~/.claude/skills/'snyk-agent-scan' (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 skillmds/skillmd shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/skillmds/skillmd.svg)](https://zalavijaysinh.github.io/skilltrust/repos/skillmds/skillmd/)

Score history