security-guidance
Claude Code · first-party · Anthropic
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.
- First seen
- 2026-04-10
- Last updated
- 2026-05-27
Metadata
{
"category": "security",
"author_email": "support@anthropic.com"
}