Open-source runtime security rules engine for MCP servers and AI agents. Detects prompt injection, command injection, jailbreaks, and data exfiltration.
Latest release v0.2.0 — prooflayer-rules v0.2.0 · 13 Jun 2026
1 file for Claude Code: prooflayer-rules CLAUDE.md — 1,938 tokens loaded in every session.
CLAUDE.md D 1,938 tok These files are sinewaveai/prooflayer-rules'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.