Agent skill · security · jeremylongshore
clade-security-basics
Secure your Anthropic integration \u2014 API key management, input validation,\n\
Why this skill is useful
Provides specific patterns and code examples for securing Anthropic API integrations, which the AI wouldn't reliably generate on its own.
What it needs
Requires anthropic account access. About 3k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Anthropic Security Basics Overview Securing a Claude integration means protecting your API key, validating inputs, defending against prompt injection, and handling user data responsibly. API Key Security Instructions Step 1: Never Expose Keys Client-Side Step 2: Environment Variables Step 3: Rotate Keys Regularly Console → Settings → API Keys → Create New Key Update all deployments with new key Delete old key only after all deployments are updated Input Validation Prompt Injection Defense Rate Limiting Your Users Data Privacy Anthropic does not train on API data by default Enable/disable data retention in API settings For HIPAA/SOC2 needs, use Anthropic's Enterprise plan Don't send unnecessary PII in prompts Checklist [ ] API key in environment variable, not in code [ ] .env in .gitignore [ ] Server-side only — no key in browser [ ] User input length limits [ ] Per-user rate limiting [ ] System prompt with injection guardrails [ ] No unnecessary PII in prompts Output API key stored securely in environment variables, not in code .env excluded from version control via .gitignore User input validated for length and content System prompt hardened against injection attempts Per-user rate limiting preventing abuse Security checklist completed Error Handling Error Cause Solution ------- ------- ---------- API Error Check error type and status code See clade-common-errors Examples See API Key Security (client-side vs server-side), Input Validation function, Prompt Injection Defense system prompt, Rate Limiting with Upstash, and Security Checklist above. Resources API Key Management Security Best Practices Data Privacy Next Steps See clade-prod-checklist for full production readiness. Prerequisites Completed clade-install-auth Server-side application (API keys must never reach the browser) Understanding of environment variable management
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/clade-security-basics