audit

A local security audit for a Claude Code setup, including configuration checks, credential scanning, and inspection of installed add-ons.

In plain words
What is it for?
Use it to review your Claude Code security posture and receive pass, warning, or failure results with an overall grade.
Why use it?
It brings several security checks into one report, helping reveal unsafe settings, exposed secrets, or suspicious plugin behavior.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/rad-security/claude-code-plugin/audit
Any agent
npx skills add rad-security/claude-code-plugin --skill audit
Clone the repo
git clone --depth 1 https://github.com/rad-security/claude-code-plugin

Made for: Claude Code, Codex.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,245 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 5 findings. Scan, not verified.
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 $0.00058 $0.02245
Opus 5 $0.00029 $0.01123
Sonnet 5 $0.00012 $0.00449
Haiku 4.5 $0.00006 $0.00225

Measured yesterday against content hash 180cf6220b67, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

audit scanned grade C with 5 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 yesterday.

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.

Reaches for credential filesmediumPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

Check if `~/.ssh/`, `~/.aws/credentials` are within the working directory tree.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ~/.claude/settings.json 2>/dev/null | grep -i sandbox

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Reads MCP configurationlowAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

cat <plugin_dir>/.mcp.json 2>/dev/null

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Unrestricted tool accesslowExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- **WARN**: Any skill has `allowed-tools: *` or includes all tools

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

grep -rn 'curl\|wget\|nc \|ncat\|eval\|exec(' <plugin_dir>/scripts/ 2>/dev/null
plugins/agentkeeper/skills/audit/SKILL.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentKeeper Claude Code Audit

You are running a comprehensive security audit of this Claude Code environment. This is the single, unified audit — it covers three sections in one pass:

  1. Setup Compliance — Claude Code configuration and environment checks
  2. Secret Exposure — scan the working directory for exposed credentials
  3. Plugin Supply Chain — audit installed plugins and skills for malicious behavior

Run all checks below, then produce a single graded report. Everything runs locally — no network calls.


Section 1: Setup Compliance

Run these checks using Bash, Read, Glob, and Grep tools. For each check, determine a result: PASS, FAIL, or WARN.

1.1 Sandbox Mode (Critical)

echo "${CLAUDE_SANDBOX:-not_set}"
cat ~/.claude/settings.json 2>/dev/null | grep -i sandbox
  • PASS: Sandbox mode is enabled or detected
  • FAIL: No sandbox detected or explicitly disabled
  • WARN: Unable to verify sandbox status

1.2 Root Execution (Critical)

id -u && whoami
  • PASS: Not running as root (uid != 0)
  • FAIL: Running as root (uid == 0)

1.3 Allowed Directories (High)

Check ~/.claude/settings.json and .claude/settings.json for allowedDirectories or directory restriction settings.

  • PASS: Allowed directories are explicitly configured with specific paths
  • WARN: Default/unrestricted directory access
  • FAIL: Explicitly set to allow all or root-level paths like /

1.4 Claude Code Version (Medium)

claude --version 2>/dev/null || echo "not_found"
  • PASS: Claude Code installed and reports a version
  • FAIL: Not found in PATH

1.5 Git Signing (Medium)

git config --global commit.gpgsign 2>/dev/null
git config --global user.signingkey 2>/dev/null
  • PASS: Commit signing enabled with a signing key
  • FAIL: No git commit signing configured

1.6 Project Settings (Medium)

test -f .claude/settings.json && echo "exists" || echo "missing"
  • PASS: .claude/settings.json exists with security-relevant configuration
  • FAIL: No .claude/settings.json in the project

Read the full file on GitHub · 239 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.

  1. yesterday First seen · 239 lines · 58 tokens per session scan C 180cf6220b67

Subscribe to this mod's changes

audit is a skill published in the GitHub repository rad-security/claude-code-plugin (2 stars, last pushed 26d ago), licensed MIT. It adds 58 tokens to every session and 2,245 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 5 findings (reaches for credential files, reads agent configuration directories, reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens