Skip to content
  1. Home
  2. Agent skills
  3. Semgrep Agent Skills

Semgrep Agent Skills

Secure-coding guidelines for agents, derived from Semgrep rules

What it is

A beta skill pack from Semgrep whose main skill gives agents secure-coding guidance grouped by impact: injection classes, XSS, XXE, path traversal, deserialisation, hard-coded secrets and infrastructure settings, across more than fifteen languages. Useful when an agent writes new code or reviews a change for vulnerabilities.

Good for

  • Check new code against OWASP Top 10 patterns
  • Review Terraform or Kubernetes config for risky settings
  • Explain a safer alternative to a flagged pattern

Install or run

npx skills add semgrep/skills

Command as given in the project README. Read the repository before you run anything on your machine.

What you need

Node.js for npx

Worth knowingMarked beta and mostly generated by converting open-source Semgrep rules; it does not run the Semgrep scanner itself.

Sources

The summary is ours, written from the README. Spotted an error? See how we work.

More for security & quality

See the topic →
  • verification-loop

    affaan-m/ECC

    Six-phase check of an agent's work ending in a PASS or FAIL report

    SkillGitHub stars: 302k
  • Requesting Code Review

    NousResearch/hermes-agent

    Pre-commit review with security scan, quality gates and auto-fix

    SkillGitHub stars: 263k
  • Web Pentest

    NousResearch/hermes-agent

    Authorized web pentest: recon, proof-based exploits and a report

    SkillGitHub stars: 263k
  • webapp-testing

    anthropics/skills

    Test local web apps with Playwright scripts

    SkillGitHub stars: 194k