Bounty Security Pattern Master Library — 399 Vulnerability Patterns
$75
A premium library of 399 vulnerability patterns and DeFi attack vectors for AI-driven bug hunting and security audits.
8
195.0(1)
Codex Skills for Security
Skills for security audits, static analysis, vulnerability triage, threat modeling, and secrets hygiene. Ship safer software with fewer surprises.
1,509 live security skills for Codex CLI.
New in Security
security audit
by Roy Yuen
$10
Professional security audit skill for web apps and APIs with structured severity-based findings and remediation plans.
5
0
truth first enterprise
by Roy Yuen
$5
Transform AI claims into verified, risk-assessed technical reports for production, DevOps, and enterprise governance.
3
1
security first
by Roy Yuen
Free
Prevent vulnerabilities before they happen by forcing early security framing and secure-by-default design patterns.
2
1074.5(2)
skill security vendor pack
by Roy Yuen
Free
Audit AI agent skills for security risks, packaging errors, and marketplace readiness with professional reports.
3
365.0(1)
cybersecurity bridge for all agentic
by Roy Yuen
Free
A high-performance wrapper to route security tasks directly to the Anthropic-Cybersecurity-Skills library.
3
41
AI Cleanroom Solutions Tool Cleanroom Design
Free
Expert AI guidance for ISO-compliant cleanroom design, HVAC filtration setup, and controlled environment installation.
2
15
skill install safety gate
by Roy Yuen
Free
Automated security and compatibility firewall for installing AI agent skills and Codex/OpenClaw packages.
2
27
dependency auditor
by Samuel Rose
$5
Audit dependencies for security, licenses, and health while generating a phased, low-risk upgrade and migration plan.
1
1
Skill Safety Scanner
$29
Scan AI agent skill definitions for malicious instructions, prompt injections, and security risks—locally.
2
0
Dependency Upgrade Planner
by Edric Vale
$5
Safe dependency upgrade plans: changelog-aware risk scoring, test hints, and rollback paths.
12
91
Claude Code Security Hooks
by Shogun Labs
$15
Pre-commit security hooks: secret detection, destructive command prevention
2
0
business ai governance mesh
by Roy Yuen
$7
A modular governance framework for AI policy, agent risk assessment, human-in-the-loop approvals, and audit trails.
2
0
campaign attribution evidence analysis
by LocoLoboZ
$12
Professional CTI analysis skill for structured attribution using ACH, Diamond Model, and confidence scoring.
2
0
agent permission boundary audit
by Roy Yuen
$5
Automated governance and risk audit for AI agent tool permissions and authentication boundaries.
2
0
Bug Bounty Triage
$15
Accelerate your bounty hunting with smart program prioritization and vulnerability report triaging for DeFi protocols.
2
0
Accessibility Auditor (WCAG 2.2)
by rayyer
$10
Find accessibility barriers and WCAG 2.2 AA failures in web and mobile UI code — with file:line, the exact criterion, and a fix
2
15.0(1)
ai security auditor
by Timoranjes
Free
Your AI agent has access to 12 tools, reads from a vector database, and executes shell commands.
2
21
Claude Code Agent Harness Setup
by Shogun Labs
$15
Project-specific Claude Code agent harness setup
2
0
industrial security zones designer
by LocoLoboZ
$15
Design and validate IEC 62443-compliant security zones and conduits for industrial (OT) networks.
2
0
🛡️ Skill Injection Scanner
$15
Review Markdown and YAML skill files for suspicious instruction patterns, with source excerpts withheld and incomplete inputs clearly flagged. Requires Python 3.12+.
1
0
MCP Server Safety Checklist
$15
Automated security auditing and risk assessment for Model Context Protocol (MCP) servers.
1
0
x402 attack surface gate
by Tate Lyman
$19
Automated launch-readiness auditor for x402 and agent-payment API surfaces.
2
0
Codex security audit skills for your codebase
A Codex security audit skill is for a backend developer or a small DevSecOps team that wants the same review routine on every repository. The skills below are community skills built as SKILL.md files, separate from any security product from OpenAI. For code and dependencies, look at security audit, dependency auditor, sast configuration and the Bounty Security Pattern Master Library. They review and report, and they do not replace a security engineer, so you check every finding yourself. For broader code checks, see our Codex code review skills.
Skills for agent and skill safety
Codex security skills also cover the agent itself. Agent permission boundary audit, MCP Server Safety Checklist, skill install safety gate and Skill Safety Scanner look at what an agent may do and what you are about to install. Use only what each description says they do, and read the listing and the scan result first, because a safety skill is itself something you run. Our guide to security audit skills and MCP explains the risks they address.
Running a security skill in Codex
Connect Codex CLI or the IDE to Agensi once, then ask for a security skill by name or let Codex choose it when your task matches. The latest approved version loads for that session and nothing is saved to .agents/skills. The MCP setup guide covers the connection. Rules that must always apply belong in AGENTS.md, which Codex always loads, unlike skills that load when relevant. For audit skills you write yourself, Codex scans .agents/skills from your working directory up to the repo root, plus $HOME/.agents/skills, and allow_implicit_invocation: false in agents/openai.yaml makes one run only on request. Our guide to installing skills in Codex CLI has the steps, and the AGENTS.md guide for Codex CLI covers the rules file.
How to choose a Codex security skill
A good Codex security skill states what it scans, and whether it only reports or also proposes fixes. Read the SKILL.md preview, then compare the use count, reviews and the scan result on the listing. Bug Bounty Triage shows the narrow kind: one job, clearly named. Pair a scan with Codex DevOps skills for pipelines, and read best security auditing skills for a wider comparison. The full range sits in the Codex skills marketplace.
Frequently asked questions
Connect an MCP-compatible agent to Agensi and ask it to use the skill on your task. Approve any required purchase. The latest approved instructions load on each use; never save skill files to disk.
Some are free, but most are paid. Paid skills show the price upfront, are a one-time purchase, and include future updates from the creator.
Yes. Every listing is checked by an 8-point automated security scan before it can go live, and the result is shown on each skill page alongside the file list.
Get in touch
Questions, partnership ideas, or feedback on the platform? Tell us what's working and what isn't, we love to hear from you!
SR
Samuel Rose
Founder & CEO of Agensi
Email UsBook a Callinfo@agensi.io
We typically respond within a few hours during business hours.