Semgrep Product Update

May 20, 2026
Detect risks in AI-generated code with Semgrep Guardian

Semgrep Guardian detects and resolves vulnerabilities in AI-generated code as it's written inside Claude Code, Cursor, Windsurf, Kiro, and other agentic coding tools. Additionally, we have shipped three curated rule packs: 27 AI Security rules covering prompt injection, unrestricted tool use, and data exfiltration; 122 Pro rules for malicious patterns in agent skill definitions; and 186 Shadow AI rules that surface LLM usage across a codebase. Autofix ships in public beta alongside it, reducing fix PRs for SAST and SCA findings from seven steps to four.

profile image
Edwin Amador Artiles