/ Directory / Playground / claude-code-owasp
← All servers ↗ GitHub
● Community agamm ⚡ Instant

claude-code-owasp

by agamm · agamm/claude-code-owasp

OWASP best practices baked into Claude Code — Top 10:2025, ASVS 5.0, Agentic AI security, plus 20+ language-specific quirks.

Claude Code OWASP Skill teaches Claude to think like a security reviewer. It loads OWASP Top 10:2025 guidance, ASVS 5.0 verification standards, the new Agentic AI security guidance, and 20+ language-specific sections (JS/TS, Python, Rust, Go, Java, Ruby, etc.). Good for pre-commit review, PR review, and threat-modeling sessions.

▶ Watch demo 📦 Install 💡 Use Cases

Why use it

Key features

Live Demo

What it looks like in practice

claude-code-owasp-skill.replay ▶ ready
0/0

Install

Author repository · Claude Skills documentation

Use Cases

Real-world ways to use claude-code-owasp

How to security-review a PR with OWASP Top 10 in mind

👤 Developers doing self-review before requesting human review ⏱ ~20 min intermediate

When to use: Before you click 'Ready for review' on a PR that touches auth, data, or input handling.

Flow
  1. Point at the diff
    Review the current PR against OWASP Top 10:2025. Focus on auth and input handling.✓ Copied
    → Findings mapped to Top 10 categories with line references
  2. Prioritize
    Group findings into 'must-fix before merge' vs 'follow-up issue'. Cite the specific ASVS requirement.✓ Copied
    → Ranked list with ASVS IDs
  3. Generate fixes
    For each must-fix, propose the minimal diff.✓ Copied
    → Patch diffs keyed to findings

Outcome: A PR that ships with known security issues resolved, with traceable requirements.

Pitfalls
  • Over-alerting on benign patterns — Ask Claude to show the exploit path concretely; if it can't, downgrade the severity

Run a lightweight threat model on a new feature

👤 Engineers designing a feature involving user data ⏱ ~40 min advanced

When to use: Design stage, before writing the code, when the blast radius is still negotiable.

Flow
  1. Describe the feature
    Feature: share-by-link for customer reports. Users generate tokenized URLs valid 7 days. Threat-model with OWASP agentic AI guidance included.✓ Copied
    → STRIDE-style list of threats
  2. Pick controls
    For each threat, what's the cheapest control that mitigates 80%?✓ Copied
    → Per-threat control + rejection rationale for expensive ones

Outcome: A threat model document you can attach to the design doc.

Pitfalls
  • Over-engineered control list — Explicitly limit to top-5 threats by likelihood × impact

Harden an AI agent integration against prompt injection

👤 Engineers shipping Claude/LLM-powered features ⏱ ~30 min advanced

When to use: You're about to let an LLM touch user data or call tools.

Flow
  1. Describe the agent surface
    Our agent reads support emails and can call 3 tools: refund(), tag_account(), escalate(). Review for agentic AI risks.✓ Copied
    → Prompt-injection vectors, tool-misuse risks, data exfil paths
  2. Design guardrails
    Propose a minimal guardrail set: which tools need human confirm, which inputs need sanitization, what logging is required.✓ Copied
    → Concrete guardrail spec

Outcome: A hardened agent design with documented guardrails.

Pitfalls
  • Relying on prompt-based defenses alone — Combine with deterministic controls — human-in-loop for destructive tools, allowlists for URLs

Audit for language-specific security quirks

👤 Reviewers checking a codebase in a language they don't know deeply ⏱ ~15 min intermediate

When to use: You're reviewing Python code as a TS native, or vice versa.

Flow
  1. Scope to language
    Review this Python module for Python-specific OWASP quirks (pickle, yaml.load, shell=True, etc.).✓ Copied
    → Language-specific findings beyond generic Top 10

Outcome: Catches that a language-agnostic review would miss.

Combinations

Pair with other MCPs for X10 leverage

claude-code-owasp-skill + claude-code-skill-factory-skill

Skill Factory wires OWASP checks as PreToolUse hooks for automatic gating

Use skill-factory /build hook to run OWASP review on every Write tool call in our repo.✓ Copied
claude-code-owasp-skill + seo-audit-skill

Overlap on security headers

Run seo-audit security category, then deeper OWASP review on the hits.✓ Copied
claude-code-owasp-skill + robotics-agent-skill

Secure ROS networking (rosbridge, Zenoh)

Robotics skill produced a rosbridge websocket — run OWASP review on it.✓ Copied

Tools

What this MCP exposes

ToolInputsWhen to callCost
Top 10:2025 review diff or files PR self-review Claude tokens
ASVS requirement check feature spec Compliance work Claude tokens
Agentic AI threat model agent design Shipping LLM features Claude tokens
Language-specific audit language, files Cross-language review Claude tokens
Threat model (STRIDE) feature description Design phase Claude tokens

Cost & Limits

What this costs to run

API quota
None
Tokens per call
5-20k per review depending on code size
Monetary
Free
Tip
Scope reviews to changed files, not the whole repo.

Security

Permissions, secrets, blast radius

Credential storage: No credentials
Data egress: Code is sent to Claude for inference

Troubleshooting

Common errors and fixes

Claude ignores OWASP context and gives generic advice

Explicitly name the guidance: 'Apply OWASP Top 10:2025 category A03:2025 Injection here.'

Too many false positives

Require an exploit walkthrough before accepting a finding

Alternatives

claude-code-owasp vs others

AlternativeWhen to use it insteadTradeoff
Semgrep / SnykYou want deterministic static analysis in CIDifferent strengths; combine both

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills

Continue exploring

Related tools and workflows

Choose another guide for your workflow, or explore a collection.

Browse all topic collections → · See 29 new official additions →