Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mfkocalar/OWASP-Security-Skills --skill owasp-security-auditgit clone --depth 1 https://github.com/mfkocalar/OWASP-Security-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mfkocalar/owasp-security-skills/owasp-security-audit)<a href="https://agentmods.dev/skills/mfkocalar/owasp-security-skills/owasp-security-audit"><img src="https://agentmods.dev/badge/skills/mfkocalar/owasp-security-skills/owasp-security-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mfkocalar/owasp-security-skills/owasp-security-audit"><img src="https://agentmods.dev/badge/skills/mfkocalar/owasp-security-skills/owasp-security-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00203 | $0.04865 |
| Opus 5 | $0.00102 | $0.02433 |
| Sonnet 5 | $0.00041 | $0.00973 |
| Haiku 4.5 | $0.00020 | $0.00487 |
Grade A, and why
owasp-security-audit scanned grade A with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Strips warnings and disclaimerslowAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- **Don't lecture.** Code-first beats essay-length background. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl $BASE/orders/1`, `/orders/2`, `…`; no special tooling, no social How it starts
The opening of the file, as written. The whole thing — 422 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OWASP Security Audit
This skill turns Claude into a rigorous security auditor that applies the right OWASP standard to the code in front of it, grounds every finding in observable evidence, and produces a structured, actionable report.
When this skill applies
Any request that asks Claude to evaluate the security of code, configuration, or a design: audits, reviews, compliance checks, hardening, threat analysis, "is this safe?" questions. Also trigger when the user pastes security-sensitive code — auth handlers, database queries, Kubernetes manifests, LLM wrappers, Keychain/Keystore calls, crypto primitives — without saying "security". That's when the value is highest.
How to route
Start by skimming references/top10.md; its patterns (broken access
control, injection, crypto misuse, misconfiguration, logging gaps)
recur under every other standard. Then load additional references
from the table below based on what the code shows.
| If you see… | Also load |
|---|---|
| HTTP handlers, form input, SQL, cookies, CSRF, XSS, HTML templates | references/top10.md (primary) |
| REST / GraphQL endpoints, JWT, OAuth, rate limiting, API gateways | references/api-top10.md |
| iOS (Swift/Obj-C), Android (Kotlin/Java), Keychain, Keystore, biometrics | references/masvs.md |
kind: Pod, ClusterRole, NetworkPolicy, Helm charts, Dockerfile |
references/kubernetes-top10.md |
| LLM SDK calls, system prompts, RAG, model output handling | references/llm.md |
| Agent loops, tool/function calling, multi-agent systems, MCP servers | references/agentic.md |
| Explicit compliance question: "what ASVS L2 requires…", "is this MASVS…" | references/asvs.md and/or references/masvs.md |
What ships with it
19 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/examples/api-auth-bypass.js 2.5 KB runs code
- assets/examples/broken-access-control.py 7.2 KB runs code
- assets/examples/cryptographic-failures.js 7.4 KB runs code
- assets/examples/injection.js 2.0 KB runs code
- assets/examples/k8s-rbac.yaml 4.5 KB
- assets/examples/logging-monitoring-failures.py 14 KB runs code
- assets/examples/prompt-injection.txt 10 KB
- assets/examples/security-misconfiguration.py 12 KB runs code
- assets/examples/xss.html 4.4 KB
- references/agentic.md 9.8 KB
- references/api-top10.md 20 KB
- references/asvs.md 9.0 KB
- references/kubernetes-top10.md 20 KB
- references/llm.md 9.7 KB
- references/masvs.md 11 KB
- references/owasp-urls.json 13 KB
- references/top10.md 28 KB
- references/vulnerable-patterns.md 9.2 KB
- scripts/quick_scan.py 11 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 422 lines · 203 tokens per session scan A 82470479205e
owasp-security-audit is a skill published in the GitHub repository mfkocalar/OWASP-Security-Skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 203 tokens to every session and 4,865 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 2 findings (strips warnings and disclaimers, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…