How do I install the Security AI Keys skill?

Run npx skillmds@latest add majiayu000/security-ai-keys-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Security AI Keys safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Security AI Keys?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Security AI Keys free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Security AI Keys?

majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Security AI Keys by majiayu000 — Agent Skill

Name: Security AI Keys
Rating: 4.2 (5 reviews)
Author: majiayu000

Security AI Keys

AI API key leakage review patterns. Use when code integrates AI providers (OpenAI, OpenRouter, Anthropic, Google/Gemini/Vertex, AWS Bedrock, Azure OpenAI, Mistral, Cohere, Groq, Replicate, Together, Perplexity, Fireworks, Hugging Face) or when env vars/keys are present. Focuses on client-side exposure, logging/redaction, and build artifacts.

majiayu000 Updated Sep 22, 2026 567 repo stars

File contents

Security audit patterns for AI API key leakage in applications integrating AI providers.

Core Principles

MUST treat AI API keys as secrets and keep them server-side.
MUST NOT ship keys to browsers or mobile clients.
SHOULD avoid logging keys; redact before logging or error reporting.
MUST rotate keys immediately if exposure is suspected.

Common Leak Paths

1) Client-Side Exposure

NEXT_PUBLIC_* / VITE_* env vars containing AI keys
Direct calls to AI provider endpoints from browser code

2) Build Artifacts

Keys embedded in bundles (dist/, build/, .next/)
Source maps exposing server code containing keys

3) Logs and Telemetry

console.log / logger statements that include key values
Error tracking payloads (Sentry, Datadog) with headers included

Quick Audit Commands

# Env files: AI keys accidentally exposed to client
rg -n "(NEXT_PUBLIC_|VITE_).*(OPENAI|OPENROUTER|ANTHROPIC|GEMINI|GOOGLE|VERTEX|BEDROCK|AWS|AZURE|MISTRAL|COHERE|GROQ|PERPLEXITY|TOGETHER|REPLICATE|FIREWORKS|HUGGINGFACE|HF_)" . -g "*.env*"

# Client code calling AI APIs directly (check for browser use)
rg -n "api\.openai\.com|openrouter\.ai|api\.anthropic\.com|generativelanguage\.googleapis\.com|aiplatform\.googleapis\.com|bedrock.*amazonaws\.com|api\.mistral\.ai|api\.cohere\.ai|api\.groq\.com|api\.together\.xyz|api\.perplexity\.ai|api\.replicate\.com|api\.fireworks\.ai|openai\.azure\.com" . -g "*.js" -g "*.ts" -g "*.jsx" -g "*.tsx" -g "*.vue"

# Scan build outputs for likely keys (heuristic)
rg -a "sk-[A-Za-z0-9]{20,}|sk-ant-[A-Za-z0-9-]{20,}|sk-or-[A-Za-z0-9-]{20,}|AIza[0-9A-Za-z_-]{35}|hf_[A-Za-z0-9]{20,}" dist/ build/ .next/ 2>/dev/null

# Service account credentials and cloud auth files
rg -n "\"type\"\s*:\s*\"service_account\"|GOOGLE_APPLICATION_CREDENTIALS|AWS_ACCESS_KEY_ID|AWS_SECRET_ACCESS_KEY|AZURE_OPENAI_API_KEY" . -g "*.env*" -g "*.json"

Hardening Checklist

AI provider keys only in server runtime (never in browser)
.env.local and .env.*.local are gitignored
Logs redact or omit secrets (request headers, env values)
Build artifacts scanned before deploy
Keys rotated if exposure suspected

Scripts

scripts/scan.sh - First-pass AI key leakage scan

---name: security-ai-keys-2description: AI API key leakage review patterns. Use when code integrates AI providers (OpenAI, OpenRouter, Anthropic, Google/Gemini/Vertex, AWS Bedrock, Azure OpenAI, Mistral, Cohere, Groq, Replicate, Together, Perplexity, Fireworks, Hugging Face) or when env vars/keys are present. Focuses on client-side exposure, logging/redaction, and build artifacts.---<overview>Security audit patterns for AI API key leakage in applications integrating AI providers.</overview><rules>## Core Principles- MUST treat AI API keys as secrets and keep them server-side.- MUST NOT ship keys to browsers or mobile clients.- SHOULD avoid logging keys; redact before logging or error reporting.- MUST rotate keys immediately if exposure is suspected.</rules><vulnerabilities>## Common Leak Paths### 1) Client-Side Exposure- `NEXT_PUBLIC_*` / `VITE_*` env vars containing AI keys- Direct calls to AI provider endpoints from browser code### 2) Build Artifacts- Keys embedded in bundles (`dist/`, `build/`, `.next/`)- Source maps exposing server code containing keys### 3) Logs and Telemetry- `console.log` / logger statements that include key values- Error tracking payloads (Sentry, Datadog) with headers included</vulnerabilities><commands>## Quick Audit Commands```bash# Env files: AI keys accidentally exposed to clientrg -n "(NEXT_PUBLIC_|VITE_).*(OPENAI|OPENROUTER|ANTHROPIC|GEMINI|GOOGLE|VERTEX|BEDROCK|AWS|AZURE|MISTRAL|COHERE|GROQ|PERPLEXITY|TOGETHER|REPLICATE|FIREWORKS|HUGGINGFACE|HF_)" . -g "*.env*"# Client code calling AI APIs directly (check for browser use)rg -n "api\.openai\.com|openrouter\.ai|api\.anthropic\.com|generativelanguage\.googleapis\.com|aiplatform\.googleapis\.com|bedrock.*amazonaws\.com|api\.mistral\.ai|api\.cohere\.ai|api\.groq\.com|api\.together\.xyz|api\.perplexity\.ai|api\.replicate\.com|api\.fireworks\.ai|openai\.azure\.com" . -g "*.js" -g "*.ts" -g "*.jsx" -g "*.tsx" -g "*.vue"# Scan build outputs for likely keys (heuristic)rg -a "sk-[A-Za-z0-9]{20,}|sk-ant-[A-Za-z0-9-]{20,}|sk-or-[A-Za-z0-9-]{20,}|AIza[0-9A-Za-z_-]{35}|hf_[A-Za-z0-9]{20,}" dist/ build/ .next/ 2>/dev/null# Service account credentials and cloud auth filesrg -n "\"type\"\s*:\s*\"service_account\"|GOOGLE_APPLICATION_CREDENTIALS|AWS_ACCESS_KEY_ID|AWS_SECRET_ACCESS_KEY|AZURE_OPENAI_API_KEY" . -g "*.env*" -g "*.json"```</commands><checklist>## Hardening Checklist- [ ] AI provider keys only in server runtime (never in browser)- [ ] `.env.local` and `.env.*.local` are gitignored- [ ] Logs redact or omit secrets (request headers, env values)- [ ] Build artifacts scanned before deploy- [ ] Keys rotated if exposure suspected</checklist><scripts>## Scripts- `scripts/scan.sh` - First-pass AI key leakage scan</scripts>

Frequently asked questions