Find AI/LLM security vulnerabilities in your code before attackers do — covers prompt injection, MCP tool poisoning, RAG data poisoning, and more
Latest release v0.12.1 — v0.12.1 — Recall corpus: MCP013 checked against published CVEs and refactors · 27 Oct 2026
1 file for Claude Code: SecureAI-Scan CLAUDE.md — 5,083 tokens loaded in every session.
CLAUDE.md C 5,083 tok These files are akanthed/SecureAI-Scan's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.