kernora-agent-security

kernora-agent-security is a plugin for Claude Code from kernora-ai/agent-sec. Its manifest loads nothing; the 1 skill, 3 commands, 1 hook it bundles cost 161 tokens per session together, scanned A, original, Apache-2.0.

A read-only security adviser for an AI coding agent, based on guidance such as OWASP, CWE, and the EU AI Act. It gives cited warnings before risky actions.

In plain words
What is it for?
Reviewing proposed coding-agent actions against common security weaknesses and relevant AI regulations.
Why use it?
It helps identify security risks and explain the guidance behind them before changes are made, without modifying or blocking the work.

Plugin for Claude Code

Install

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.

Claude Code
/plugin marketplace add kernora-ai/agent-sec
agentmods
npx agentmods add plugins/kernora-ai/agent-sec/kernora-agent-security
Clone the repo
git clone --depth 1 https://github.com/kernora-ai/agent-sec

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill, 3 commands, 1 hook cost 161 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

kernora-agent-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 3d 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.

plugins/kernora-agent-security/.claude-plugin/plugin.json · 14 lines

What it actually says

{
  "name": "kernora-agent-security",
  "version": "0.1.0",
  "description": "Grounds your AI coding agent in a cited security baseline (OWASP/CWE/EU AI Act) and warns before risky actions. Advisory, free, read-only. Real-time blocking is Kernora Axiora.",
  "author": { "name": "Kernora", "url": "https://kernora.ai" },
  "homepage": "https://agentsec.kernora.ai",
  "repository": "https://github.com/kernora-ai/agent-sec",
  "license": "Apache-2.0",
  "keywords": ["security", "mcp", "ai-agents", "claude-code", "owasp"],
  "mcpServers": {
    "agentsec": { "type": "http", "url": "https://agentsec.kernora.ai/mcp" }
  }
}
Contents

What it installs

The manifest is a name and a version. 1 skill, 3 commands, 1 hook travel with it, and installing the plugin installs all of them — 161 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

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.

  1. 3d ago First seen · 14 lines scan A 4839c69fb8cb

Subscribe to this mod's changes

kernora-agent-security is a plugin published in the GitHub repository kernora-ai/agent-sec (1 stars, last pushed 1mo ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

Related

Other plugins, from other repositories

security-agent-skills

Security-testing methodology as portable agent skills, spanning white-box bug hunting, AI-agent and LLM red-teaming, cloud identity and CI/CD trust, client-app trust surfaces across browser and editor extensions and Electron, wire-protocol and token trust across gRPC, WebSocket, and JWT, infrastructure-as-code and…

UnboundCompute/security-agent-skills · not measured

agentguards-claude

LLM security guardrails for Claude Code — jailbreak detection, prompt-injection and web-content scanning, data-exfiltration blocking, and destructive-command authorization. Bundles the AgentGuards MCP server plus enforcing hooks.

alelaguard/agentguards-plugins · not measured

agentguards-claude-selfhosted

LLM security guardrails for Claude Code, for a self-hosted AgentGuards appliance — jailbreak detection, prompt-injection and web-content scanning, data-exfiltration blocking, and destructive-command authorization, enforced entirely by hooks. No bundled MCP server: Claude Code's .mcp.json cannot point at a…

alelaguard/agentguards-plugins · not measured

trust-issues

Adversarial, attacker-minded security review of untrusted code before you install it. A read-only scanner plus a five-persona reasoning pass, ending in a GO / GO-WITH-MITIGATIONS / NO-GO verdict.

howshannon/trust-issues · not measured

bridgeward

Skeptical-reading and prompt-injection defense for AI coding agents. Trust nothing. Ship safely.

bridge-mind/BridgeWard · not measured

ai-app-security

Security guardrails for AI-built apps: OWASP/API/LLM/MCP rules applied while building, an /audit skill for full reviews, and a hook that blocks secret commits.

xChechi/xche-ai-app-security-pack · not measured