by semgrep
A collection of skills for AI coding agents from Semgrep
# Add to your Claude Code skills
git clone https://github.com/semgrep/skillsLast scanned: 5/30/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-30T15:34:21.870Z",
"npmAuditRan": true,
"pipAuditRan": true
}skills is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by semgrep. A collection of skills for AI coding agents from Semgrep. It has 232 GitHub stars.
Yes. skills passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/semgrep/skills" and add it to your Claude Code skills directory (see the Installation section above).
skills is primarily written in JavaScript. It is open-source under semgrep on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh skills against similar tools.
No comments yet. Be the first to share your thoughts!
A collection of skills for AI coding agents. Skills are packaged instructions and scripts that extend agent capabilities. This should be considered beta-level software; it's primarily generated by transforming open-source Semgrep rules into skill format.
Skills follow the Agent Skills format.
npx skills add semgrep/skills
Comprehensive code security guidelines from Semgrep Engineering covering OWASP Top 10, infrastructure security, and secure coding best practices across 15+ languages.
Use when:
Categories covered:
| Impact | Category | Description |
|---|---|---|
| Critical | SQL Injection | Parameterized queries, ORM safety |
| Critical | Command Injection | Shell command safety, input validation |
| Critical | Cross-Site Scripting (XSS) | Output encoding, DOM safety |
| Critical | XML External Entity (XXE) | XML parser configuration |
| Critical | Path Traversal | File path validation |
| Critical | Insecure Deserialization | Safe deserialization patterns |
| Critical | Code Injection | Eval safety, template injection |
| Critical | Hardcoded Secrets | Environment variables, secret management |
| Critical | Memory Safety | Buffer overflows, use-after-free (C/C++) |
| High | Insecure Cryptography | Strong hashing (SHA-256+), encryption (AES) |
| High | Insecure Transport | HTTPS, certificate validation, TLS |
| High | Server-Side Request Forgery | URL validation, allowlists |
| High | JWT Authentication | Signature verification, algorithm safety |
| High | Cross-Site Request Forgery | CSRF tokens, SameSite cookies |
| High | Prototype Pollution | Object key validation (JavaScript) |
| High | Unsafe Functions | Dangerous function alternatives |
| High | Terraform AWS | S3, IAM, EC2, RDS security |
| High | Terraform Azure | Storage, App Service, Key Vault |
| High | Terraform GCP | GCS, GCE, GKE, IAM |
| High | Kubernetes | Pod security, RBAC, secrets |
| High | Docker | Non-root containers, image pinning |
| High | GitHub Actions | Script injection, action pinning |
| Medium | Regex DoS | Catastrophic backtracking prevention |
| Medium | Race Conditions | TOCTOU, secure temp files |
| Medium | Code Correctness | Common bugs, type errors |
| Low | Best Practices | Code quality patterns |
| Low | Performance | Efficiency anti-patterns |
| Low | Maintainability | Code organization |
Languages: Python, JavaScript/TypeScript, Java, Go, Ruby, PHP, C/C++, C#, Scala, Kotlin, Rust, HCL (Terraform), YAML (Kubernetes)
Security guidelines for LLM applications based on the OWASP Top 10 for Large Language Model Applications 2025.
Use when:
Categories covered:
| Impact | Category | Description |
|---|---|---|
| Critical | Prompt Injection | Input validation, content segregation, output filtering |
| Critical | Sensitive Information Disclosure | PII detection, permission-aware RAG |
| Critical | Supply Chain | Model verification, safetensors, ML-BOM |
| Critical | Data and Model Poisoning | Training data validation, anomaly detection |
| Critical | Improper Output Handling | Context-aware encoding, parameterized queries |
| High | Excessive Agency | Least privilege, human-in-the-loop |
| High | System Prompt Leakage | External guardrails, no secrets in prompts |
| High | Vector and Embedding Weaknesses | Permission-aware retrieval, tenant isolation |
| High | Misinformation | RAG, fact verification, confidence scoring |
| High | Unbounded Consumption | Rate limiting, budget controls |
Frameworks: OWASP LLM Top 10, MITRE ATLAS, NIST AI RMF
Run Semgrep static analysis scans and create custom detection rules for security vulnerabilities and bug patterns.
Use when:
Capabilities:
| Feature | Description |
|---|---|
| Quick Scans | Run semgrep --config auto or use curated rulesets |
| Rulesets | security-audit, owasp-top-ten, cwe-top-25, trailofbits |
| Custom Rules | Pattern matching and taint mode for data flow analysis |
| Test-Driven | Write test cases first with ruleid: and ok: annotations |
| CI/CD | GitHub Actions integration with diff-aware scanning |
Rule Creation Workflow:
semgrep --dump-astWhen to use taint mode: SQL injection, command injection, XSS, path traversal, SSRF - any vulnerability where untrusted data flows to a dangerous sink.
Skills are automatically available once installed. The agent will use them when relevant tasks are detected.
Examples:
Review this React component for security issues
Help me implement input validation for my LLM chat endpoint
Create a Semgrep rule to detect hardcoded API keys in Python
make install # Install dependencies
make validate # Validate all skills
make build # Build AGENTS.md for all skills
make zip # Create distribution packages
make # All of the above
make validate-skill SKILL=code-security
make build-skill SKILL=llm-security
Each skill contains:
SKILL.md - Instructions for the agentrules/ - Individual rule files (for skills with rules)scripts/ - Helper scripts for automation (optional)references/ - Supporting documentation (optional)Originally created by @DrewDennison at Semgrep. This work was heavily inspired by Vercel's React Best Practices.