clawvisor

PinchBench is a benchmarking system for evaluating LLM models as OpenClaw coding agents. Made with 🦀 by the humans at https://kilo.ai

Proactive security monitoring skill for OpenClaw with a 41-point scanner detecting ClawHavoc malicious skills (824+ entries), AMOS stealer, memory poisoning, supply chain attacks, and 60+ CVEs, with web dashboard and Telegram alerting.

Multi-agent AI gateway with teams, delegation & orchestration. Single Go binary, 11+ LLM providers, 5 channels.

Semgrep's official security skills collection that packages code scanning rules, vulnerability detection, and remediation guidance into SKILL.md format, enabling AI coding assistants to proactively identify and fix security issues during development.