agentnode-dev publishes skills that help AI agents audit other agent skills before they are installed or re-checked over time. Their most popular skill checks for prompt injection, data exfiltration, malicious commands, obfuscated code, privilege abuse, supply chain risks, and memory poisoning across platforms such as Claude Code and OpenClaw. The focus of their work is security review of agent skills themselves.
Skills Security Audit
1 skills · 1 stars
Skills Security Audit Audit AI agent skills for security risks before installation or periodically.