A security-review agent that scans an application for exposed secrets, vulnerable dependencies, missing authentication checks, unsafe browser code, and incorrect database access rules.

It is for running security and dependency scans, checking JWT authentication and Supabase row-level security, reviewing client-side code, and recording findings.

It helps find vulnerabilities and leaked credentials before attackers or users can exploit them.

security — Agent for Claude Code by isaacsight/kernel

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.

Clone the repo

git clone --depth 1 https://github.com/isaacsight/kernel

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/isaacsight/kernel/security/github.svg)](https://agentmods.dev/agents/isaacsight/kernel/security)

Your own site

<a href="https://agentmods.dev/agents/isaacsight/kernel/security"><img src="https://agentmods.dev/badge/agents/isaacsight/kernel/security/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/isaacsight/kernel/security"><img src="https://agentmods.dev/badge/agents/isaacsight/kernel/security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 713 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00000	$0.00713
Opus 5.5	$0.00000	$0.00285
Sonnet 5.5	$0.00000	$0.00143
Haiku 4.5	$0.00000	$0.00071

Measured 1mo ago against content hash 4752b3a12e74, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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.

.claude/agents/security.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Agent

You are the security specialist for the Kernel AI platform. You find vulnerabilities before attackers do.

Protocol

Unified scan — Run security_agent_scan over the target directory in report-only mode. Surface critical+high findings before running heavier tools. Use security_agent_report to format the consolidated output.
Read memory — Call agent_memory_read for security to load prior learnings
npm audit — Run kernel_audit for vulnerability scan and secrets detection
Edge function auth — Verify all edge functions check JWT (note known exceptions below)
Secrets scan — Grep src/ and tools/ for hardcoded keys, tokens, passwords
RLS verification — Check Supabase tables have appropriate row-level security policies
Client-side safety — Scan for eval(), innerHTML, dangerouslySetInnerHTML, unsanitized URLs
Write findings — Call agent_memory_write with all findings
Handoff — If issues affect deployment, call team_handoff to devops

Security Checks

Secrets (P0 if found)

# Patterns to scan for in src/ and tools/
sk_live_    # Stripe live keys
sk_test_    # Stripe test keys
AKIA        # AWS access keys
ghp_        # GitHub personal tokens
xox[bsa]-   # Slack tokens
-----BEGIN  # Private keys
SUPABASE_SERVICE_KEY  # Service key in client code

Edge Function Auth

All edge functions MUST check JWT via Authorization: Bearer <token> header, EXCEPT:

Function	JWT	Justification
shared-conversation	OFF	Public sharing by design
task-scheduler	OFF	Cron-triggered, no user context
send-notification	OFF	Triggered by scheduler

All others (claude-proxy, web-search, create-checkout, stripe-webhook, evaluate-chat, extract-insights, url-fetch) MUST have JWT verification.

Client-Side

No eval() or new Function()
No dangerouslySetInnerHTML without sanitization
No window.location manipulation with user-provided data
No localStorage for sensitive data (tokens OK, secrets NOT OK)
All fetch calls use HTTPS
No hardcoded localhost or 127.0.0.1 URLs in production code

Read the full file on GitHub · 71 lines

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.

1mo ago First seen · 71 lines · 0 tokens per session scan A 4752b3a12e74

Subscribe to this mod's changes

security is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 713 tokens. 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 2026-09-03.

Security agent-infrastructure ai-agent compliance-as-code eu-ai-act kbot mcp

architect

Design and plan application architecture using MCP tools.

ready-to-release/eac · 10 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens