Agent Plugins Marketplace
← All plugins

ai-data-security

v0.2.0

Data + AI security audits for data professionals — cited, severity-ranked findings for AI tool configs, secrets exposure, data classification, and warehouse access.

Claude Code5 Skills

By Kyle ChalmersLicense: MIT0 GitHub starsUpdated last week

Directory evidence

Runtimes
Claude Code
Parsed components
5 skill or MCP entries
Source updated
Sep 12, 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 ai-data-security for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install ai-data-security@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

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/kyle-chalmers/ai-data-security

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

Plugin files

ai-data-security/
├── .claude-plugin/plugin.json
├── skills/ai-config-audit/SKILL.md
├── skills/data-classification/SKILL.md
├── skills/db-access-audit/SKILL.md
├── skills/secrets-scanner/SKILL.md
└── skills/security-audit/SKILL.md

Included Skills5

ai-config-auditskills/ai-config-audit/SKILL.md

Audit AI coding-tool configuration for data-safety risks — permission deny/allow rules for secrets, MCP configs across Claude/Cursor/Gemini/Codex, plaintext transcript exposure, retention/training tier guidance. Read-only; cited findings; never prints config values.

data-classificationskills/data-classification/SKILL.md

Classify a repo's files against the 4-tier data sensitivity framework (Public / Internal / Confidential / Restricted) with validated-content evidence, and flag Restricted/Confidential data sitting where AI tools can read it. Read-only; reports carry counts and column names, never data values.

db-access-auditskills/db-access-audit/SKILL.md

Read-only warehouse audit for AI access risk — over-broad grants held by the AI principal, unmasked PII columns, missing masked-view layer, missing audit logging. Postgres (live) and Snowflake (recorded/live) SQL packs. Human-gated; connects via your own pre-authenticated psql/snow; never stores credentials.

secrets-scannerskills/secrets-scanner/SKILL.md

Scan a repo for secrets on disk and in git history (gitleaks), then compute what gitleaks can't — whether each secret is agent-readable, gitignored-but-exposed, or already pushed to a remote. Read-only; cited, severity-ranked findings; never prints secret values.

security-auditskills/security-audit/SKILL.md

The ~30-minute end-to-end data + AI security audit — orchestrates secrets-scanner, ai-config-audit, data-classification, and (optionally) db-access-audit into one prioritized, deduplicated, cited report. Read-only.

Plugin manifests1

.claude-plugin/plugin.json
{
  "$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
  "name": "ai-data-security",
  "displayName": "AI Data Security",
  "version": "0.2.0",
  "description": "Data + AI security audits for data professionals — cited, severity-ranked findings for AI tool configs, secrets exposure, data classification, and warehouse access.",
  "author": {
    "name": "Kyle Chalmers"
  },
  "repository": "https://github.com/kyle-chalmers/ai-data-security",
  "license": "MIT",
  "keywords": [
    "security",
    "data",
    "ai-security",
    "pii",
    "secrets",
    "audit",
    "data-warehouse"
  ]
}

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.

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