agentmods.dev

security-audit

security-audit is a command for Claude Code from isaacsight/kernel. It costs 0 tokens per session (482 once invoked), scanned A, original, MIT.

A security-audit command for checking a web platform's dependencies, source code, authentication, and database access rules.

In plain words
What is it for?
Use it to scan for secrets and unsafe code, verify Edge Function authentication, check environment-file protection, and review database security policies.
Why use it?
It helps find vulnerable packages, exposed credentials, unsafe browser code, missing authentication checks, and tables without suitable row-level security policies.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

not rated 16repo 1mo ago A scan 0 tokens original MIT

Good fit Use it to scan for secrets and unsafe code, verify Edge Function authentication, check environment-file protection, and review database security policies.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/isaacsight/kernel/security-audit
View source ↗ isaacsight/kernel kernel.chat
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.

agentmods badge for security-audit

README.md
[![agentmods](https://agentmods.dev/badge/commands/isaacsight/kernel/security-audit/github.svg)](https://agentmods.dev/commands/isaacsight/kernel/security-audit)
Your own site
<a href="https://agentmods.dev/commands/isaacsight/kernel/security-audit"><img src="https://agentmods.dev/badge/commands/isaacsight/kernel/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.

agentmods 80×15 button for security-audit

Your own site · 80×15
<a href="https://agentmods.dev/commands/isaacsight/kernel/security-audit"><img src="https://agentmods.dev/badge/commands/isaacsight/kernel/security-audit.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 482 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00482
Opus 5.5 $0.00000 $0.00193
Sonnet 5.5 $0.00000 $0.00096
Haiku 4.5 $0.00000 $0.00048

Measured 2mo ago against content hash f4dd72b93e54, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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.

.claude/commands/security-audit.md · 47 lines

What it actually says

Run a full security audit on the Kernel platform.

You are the Security Agent. Read .claude/agents/security.md for your full protocol and known exceptions.

Steps:

  1. Load memory — Call agent_memory_read for security agent
  2. npm audit — Run kernel_audit for vulnerability scan and secrets detection
  3. Secrets scan — Grep source code for hardcoded keys:
    • Search src/ and tools/ for: sk_live_, sk_test_, AKIA, ghp_, xox[bsa]-, -----BEGIN, SUPABASE_SERVICE_KEY
    • Check that .env is in .gitignore
  4. Edge function auth — For each edge function in supabase/functions/, verify JWT checking:
    • claude-proxy: MUST have JWT
    • web-search: MUST have JWT
    • create-checkout: MUST have JWT
    • stripe-webhook: Uses Stripe signature (OK)
    • shared-conversation: verify_jwt=false (KNOWN EXCEPTION)
    • task-scheduler: verify_jwt=false (KNOWN EXCEPTION)
    • send-notification: verify_jwt=false (KNOWN EXCEPTION)
  5. Client-side safety — Scan src/ for:
    • eval( or new Function(
    • dangerouslySetInnerHTML without sanitization
    • Hardcoded localhost or 127.0.0.1 URLs
  6. RLS check — Run kernel_db_schema and verify tables have appropriate RLS policies
  7. CORS check — Verify all edge functions include proper CORS headers
  8. Save findings — Call agent_memory_write for security with findings
  9. Handoff — If issues affect deployment, call team_handoff to devops

Report format:

# Security Audit — [date]

## Vulnerabilities (npm)
[critical/high/moderate/low counts]

## Secrets Scan
[PASS or findings]

## Edge Function Auth
[table of functions and their auth status]

## Client-Side Safety
[PASS or findings]

## Verdict: PASS / FAIL (any P0 = FAIL)
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. 2mo ago First seen · 47 lines · 0 tokens per session scan A f4dd72b93e54

Subscribe to this mod's changes

security-audit is a command 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 482 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.

Backend and APIsSecurityagent-infrastructureai-agentcompliance-as-codeeu-ai-actkbotmcp
Related

security-audit compared with commands from other repositories

security-audit next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
security-auditisaacsight/kernelCommand161mo agoMITA0Claude Code
buildAzure/ai-gatewayCommand510d agoMITA0Claude Code
api-contract-reviewMozurok/fhorja.devCommand1028d agoMITA64Claude Code
symfony-api-mcpgerard-labs/superpowers-api-platformCommand25mo agoMITA17Claude Code
add-api-railwayAshikparvez89/larouex-fullstack-pluginCommand324d agoMITA0Claude Code
multi-backendRohitBind123/claude-setupCommand26mo agoMITA0Claude Code
checklistgithub/spec-kitCommand148kyesterdayMITA13Claude Code