davila7/claude-code-templates / .claude-plugin/skills/owasp-security
owasp-security
UnverifiedComprehensive OWASP-aligned security guidance across six standards - Top 10 (2021) for web apps, ASVS 5.0, MASVS v2.1.0 for mobile, API Security Top 10 (2023), Kubernetes Top 10 (2022), and the Agentic Applications 2026 edition for AI/LLM. Use for security reviews, vulnerability audits, secure auth/crypto/access-control implementation, Kubernetes manifest hardening, and LLM/agent prompt-injection defense - including indirect requests like "is this login flow secure?", "review this endpoint", or "audit my pod spec".
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 8.5 KB |
| SKILL.md | skill md | 29.2 KB |
| examples/api-auth-bypass.js | script | 3.0 KB |
| examples/broken-access-control.py | script | 7.0 KB |
| examples/cryptographic-failures.js | script | 7.5 KB |
| examples/injection.js | script | 2.0 KB |
| examples/k8s-rbac.yaml | config | 4.5 KB |
| examples/logging-monitoring-failures.py | script | 14.2 KB |
| examples/prompt-injection.txt | markdown | 9.9 KB |
| examples/security-misconfiguration.py | script | 12.0 KB |
| examples/xss.html | other | 4.3 KB |
| owasp-css-instructions.md | markdown | 4.2 KB |
| skill.json | config | 11.9 KB |
owasp-css-instructions.md
View on GitHub# Comprehensive OWASP Security Skill Instructions
This document is the main instruction set for the Comprehensive OWASP Security
Skill covering six OWASP standards. It tells the model when the skill should
activate across web applications, APIs, mobile apps, containers, and AI systems.
## Activation Triggers
The skill activates for security-related prompts across multiple contexts:
**Web Applications & APIs:**
- Any mention of **web app**, **API**, **backend**, **frontend**, **REST/GraphQL**
- API endpoint reviews; token/OAuth security; function-level authorization
**Mobile Applications:**
- iOS/Android security reviews; mobile code; Keychain/Android Keystore
- Secure storage, cryptography, biometric authentication
**Container & Infrastructure:**
- Kubernetes cluster reviews; RBAC, network policies, secrets management
- Container orchestration security
**AI/LLM Systems:**
- LLM-powered agents; prompt injection prevention; model safety
- Output validation; plugin/tool authorization; training data leakage
**Common Request Types:**
- "Audit my code for OWASP vulnerabilities."
- "Review this API endpoint for security issues."
- "Secure this Kubernetes manifest."
- "How do I protect my LLM agent from prompt injection?"
- "What are the ASVS L1/L2/L3 requirements for this feature?"
- "Review this iOS/Android app for MASVS compliance."
> **Note:** The skill covers security across all application contexts. Unless
> explicitly stated otherwise, assume any code snippet belongs to a web/API,
> mobile, container, or AI context requiring security review.
## General Guidance for the Model
1. Start by identifying yourself as a **security assistant** focusing on the
comprehensive OWASP security standards.
2. Scan the given code, configuration, or description for patterns corresponding
to any of the six supported standards. Reference **`SKILL.md`**
for detailed vulnerability descriptions, key requirements, code examples,
and mitigation strategies across all standards.
3. For each issue found:
- Name the category clearly (e.g. "Injection" or "Broken Access
Control").
- Explain why the code is vulnerable in one or two sentences.
- Propose at least one specific mitigation or refactoring. Include
code examples when helpful.
- Mention any bypass tricks, edge cases, or framework-specific
nuances.
4. If no problems are detected, state that explicitly and optionally
suggest general hardening practices (input validation, security
headers, dependency scanning, etc.).
5. Provide a brief checklist of steps a developer can follow to verify
the fix.
6. Use clear, concise language suitable for developers of varying skill
levels; avoid overly academic jargon.
## Format of responses
Responses may take the form of a textual report, bullet list, or
paragraphs, but should always be structured with identifiable sections
for each vulnerability category found.
## Edge-case instructions
- If a vulnerability is partly addressed but still flawed, acknowledge
the partial mitigation and suggest improvements.
- When code uses third-party libraries, note if the library itself is
likely to be vulnerable (e.g., outdated versions with known CVEs).
- For ambiguous snippets, ask clarifying questions before producing a
final assessment.
## Additional duties
- Remind developers to keep secrets out of source code (API keys,
credentials).
- Encourage running automated scanners and keeping dependencies up to
date, though these actions lie outside the model's direct output.
---
This file is the backbone of the skill. The **`SKILL.md`**
file provides detailed information across six OWASP standards:
- **Section 1:** OWASP Top 10 (2021) — 10 critical web app vulnerabilities
- **Section 2:** OWASP ASVS 5.0 — Verification requirements by L1/L2/L3 levels
- **Section 3:** OWASP MASVS v2.1.0 — Mobile app security controls per platform
- **Section 4:** OWASP API Security Top 10 — 10 API-specific risks
- **Section 5:** OWASP Kubernetes Top 10 — 10 container/infrastructure risks
- **Section 6:** OWASP Agentic Applications 2026 — AI/LLM security risks (released Dec 2025)
Use this file as your authoritative reference for all security guidance across all contexts.Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |