Agent Plugins Marketplace
← All plugins

claude-security-audit

v0.1.4

Static-analysis security audit for agent project configs, marketplaces, hooks, MCP, and secrets.

CodexClaude Code1 Skill

By PrasLicense: MIT0 GitHub starsUpdated 2 weeks ago

Directory evidence

Runtimes
Codex and Claude Code
Parsed components
1 skill or MCP entry
Source updated
Oct 4, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install claude-security-audit for Codex and Claude Code

Installs for the current user
codex plugin marketplace add pulseai-labs/claude-agent-scaffolding
codex plugin marketplace upgrade claude-agent-scaffolding-codex
codex plugin add claude-security-audit@claude-agent-scaffolding-codex

Paste and run these commands in a terminal with Codex. They add and refresh the claude-agent-scaffolding-codex catalog, then install this plugin.

Compatibility: the page URL and API slug “claude-security-audit” remain stable.

  • Codex: claude-security-audit@agent-plugin-marketplace → claude-security-audit@claude-agent-scaffolding-codex

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/pulseai-labs/claude-agent-scaffolding

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is claude-security-audit/.

Plugin files

claude-security-audit/
├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
└── skills/auditing-claude-configs/SKILL.md

Included Skills1

auditing-claude-configsskills/auditing-claude-configs/SKILL.md

Static-analysis security audit for Claude Code and Codex project configurations and enabled plugins. Detects secrets, permission issues, hook injection, MCP misconfiguration, settings-schema typos, prompt-injection in agents/commands, marketplace integrity issues. Activate on "audit my claude config", "audit my codex config", "security scan my .claude", "security scan my .codex", "scan for leaked credentials", "review my permissions", "audit settings.json", "apply fix SA-...", "/security-audit", "/secrets-scan", "/permissions-review", "/apply-fix". Inspired by AgentShield in Everything Claude Code (Mustafa, 2026; MIT) — independent MIT implementation tailored to composable plugin marketplaces.

Plugin manifests2

claude-security-audit/.codex-plugin/plugin.json
{
  "name": "claude-security-audit",
  "version": "0.1.4",
  "description": "Static-analysis security audit for agent project configs, marketplaces, hooks, MCP, and secrets.",
  "author": {
    "name": "Pras"
  },
  "homepage": "https://github.com/draco28/claude-agent-scaffolding/tree/main/claude-security-audit",
  "repository": "https://github.com/draco28/claude-agent-scaffolding",
  "license": "MIT",
  "keywords": [
    "security",
    "audit",
    "marketplace",
    "secrets",
    "hooks"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "Claude Security Audit",
    "shortDescription": "Audit agent project configs and plugin marketplaces.",
    "longDescription": "Claude Security Audit scans agent project configuration, enabled plugins, marketplaces, hooks, MCP settings, command prompts, and secrets. The Codex build adds Codex-specific config and marketplace targets while preserving Claude Code checks.",
    "developerName": "Pras",
    "category": "Security",
    "capabilities": [
      "Interactive",
      "Read",
      "Write"
    ],
    "defaultPrompt": [
      "Run a security audit for this agent project.",
      "Scan this project for leaked credentials.",
      "Review Claude and Codex marketplace security."
    ],
    "websiteURL": "https://github.com/draco28/claude-agent-scaffolding/tree/main/claude-security-audit",
    "brandColor": "#DC2626"
  }
}
claude-security-audit/.claude-plugin/plugin.json
{
  "name": "claude-security-audit",
  "version": "0.1.4",
  "description": "Static-analysis security audit for Claude Code project configurations and enabled plugins. 28 rules across 7 aspects (secrets, permissions incl. PERM-005 schema-typo, hooks, MCP, CLAUDE.md, prompt-injection, marketplace). Two-flag auto-fix + 5-layer defense-in-depth (T2-H). Durable finding_uid survives whitespace edits (T2-I). Self-tamper detection (T1-F). Zero ambient surface (T1-C — SessionStart reminder is opt-in). Inspired by AgentShield in Everything Claude Code (Mustafa, 2026; MIT).",
  "author": {
    "name": "Pras"
  },
  "license": "MIT",
  "homepage": "https://github.com/draco28/claude-agent-scaffolding/tree/main/claude-security-audit",
  "category": "security"
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[claude-security-audit on Agent Plugins Marketplace](https://pluginsmp.com/plugins/claude-security-audit)