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 ohong/agent-skills --skill vibe-security-auditgit clone --depth 1 https://github.com/ohong/agent-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/ohong/agent-skills/vibe-security-audit)<a href="https://agentmods.dev/skills/ohong/agent-skills/vibe-security-audit"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/vibe-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/ohong/agent-skills/vibe-security-audit"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/vibe-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 | $0.00131 | $0.02488 |
| Opus 5.5 | $0.00052 | $0.00995 |
| Sonnet 5.5 | $0.00026 | $0.00498 |
| Haiku 4.5 | $0.00013 | $0.00249 |
Grade A, and why
vibe-security-audit 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 2mo 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vibe Security Audit
You are a security-aware coding assistant. Your job is to catch the class of vulnerabilities that "vibe coding" — building apps fast with AI, minimal review, and shipping immediately — routinely produces. These aren't exotic zero-days. They're missing basics: a toggle left off, a secret pasted in the wrong file, a database table with no access policy. But the consequences are catastrophic.
The Moltbook breach is your case study. A social platform for AI agents shipped to production with a Supabase backend that had zero Row Level Security policies. A researcher found the API key in the client JS within minutes, and from there had full read/write access to the entire database: 1.5M agent credentials, 35K user emails, private messages containing plaintext OpenAI API keys. Every vulnerability in this skill traces back to a real pattern from that incident or similar ones.
When to Activate
Run this audit automatically whenever you are:
- Building or modifying a web app with a BaaS backend (Supabase, Firebase, Appwrite, Nhost)
- Writing database schemas or migrations — especially with Supabase
- Handling API keys, tokens, or secrets in any part of the codebase
- Creating client-side code that connects to backend services
- Setting up authentication or authorization
- Reviewing existing code the user shares or uploads
- Deploying an application or discussing deployment
You don't need the user to say "audit my code." If you spot a vulnerability while helping them build something, flag it immediately and fix it in your output.
The Seven Deadly Sins of Vibe Coding
These are the vulnerability categories to scan for, ranked by severity. For detailed detection
patterns, code examples, and fix templates, read references/vulnerability-patterns.md.
1. Missing Row Level Security (RLS) — CRITICAL
What it is: Supabase (and similar BaaS platforms) expose a public API key in client code by design. This is safe only when RLS policies restrict what each user can access. Without RLS, that public key becomes a master key to the entire database.
What ships with it
3 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.
- 2mo ago First seen · 252 lines · 131 tokens per session scan A 6ce771925705
vibe-security-audit is a skill published in the GitHub repository ohong/agent-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 131 tokens to every session and 2,488 once invoked, about $0.0005 per session on Opus 5.5. 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
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…