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 JoseArron/skills --skill audit-securitygit clone --depth 1 https://github.com/JoseArron/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/josearron/skills/audit-security)<a href="https://agentmods.dev/skills/josearron/skills/audit-security"><img src="https://agentmods.dev/badge/skills/josearron/skills/audit-security.svg" alt="Measured on agentmods" 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 | $0.00153 | $0.01653 |
| Opus 5 | $0.00077 | $0.00826 |
| Sonnet 5 | $0.00031 | $0.00331 |
| Haiku 4.5 | $0.00015 | $0.00165 |
Grade A, and why
audit-security scanned grade A with 0 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 6d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Security
Find where untrusted data crosses a trust boundary without the right check, and close the gap without breaking the feature. Approach the code as a bug hunter: assume every input is hostile until a server-side check proves otherwise.
Examples lean on a web stack (HTTP, a browser, an ORM, JWT) because that is where these bugs cluster, but the boundaries apply to any stack — swap the mechanism for whatever yours uses.
Glossary
- Trust boundary — the line untrusted data crosses on its way into a sensitive operation: network → app, input → interpreter, app → browser, one principal → another's resource. Every vulnerability here is data crossing one of these without the check that boundary demands.
- Fail closed — on any error, ambiguity, or missing check, deny. A thrown exception must not land the user inside the protected action.
- Least privilege — every principal, token, and database role gets the minimum scope the task needs, nothing held "just in case".
- Server-side truth — every security decision is re-made on the server. Client-side checks are UX, never enforcement; a control the user cannot see is still reachable by a crafted request.
- Defense in depth — no single control is the only thing standing between an attacker and the asset.
Axes
A security audit walks six trust boundaries. Each has a detail file with the smells, heuristics, and fixes for that boundary. Read the relevant file before classifying a finding — the heuristic is the citation, not a hunch.
- Access control — can this principal perform this action on this specific resource? IDOR, horizontal/vertical access, privilege escalation, mass assignment, tenant isolation, account lifecycle. See ACCESS-CONTROL.md.
- Auth & sessions — is the requester who they claim, is the session valid, and is this state change intentional? Password storage, JWT, cookie/session security, CSRF. See AUTH-AND-SESSIONS.md.
- Injection — does untrusted input reach an interpreter as code or structure? SQL, XXE, path traversal, command/template injection. See INJECTION.md.
- XSS & output — is untrusted data rendered into a browser context unencoded? Reflected/stored/DOM XSS, contextual encoding, CSP, sniffing/framing headers. See XSS.md.
- Untrusted URLs & uploads — does the server fetch a URL or accept a file it did not originate? SSRF, open redirect, insecure file upload. See SSRF-AND-UPLOADS.md.
- Data exposure — do secrets or sensitive data reach where they should not be visible? Secrets in client code, PII handling, transport headers, leaky errors. See DATA-EXPOSURE.md.
What ships with it
6 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.
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.
- 6d ago First seen · 93 lines · 153 tokens per session scan A b9c191669fa9
audit-security is a skill published in the GitHub repository JoseArron/skills (2 stars, last pushed 19d ago), licensed MIT. It adds 153 tokens to every session and 1,653 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. 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…