14 packages found
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
AI Agent Security Middleware — 8-layer defense, DLP data flow, prompt injection detection, zero dependencies. SDK + MCP
Skill Scan Agent — Automated scanning, identification, and assessment of SKILL security risks.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development f
Deterministic LLM prompt defense scanner — 12 attack vectors, pure regex, zero AI cost, < 5ms
The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai
Skill for Claude Code / OpenAI Codex: audit a reference site and produce a differentiated parity plan (UI, interactions,
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewritin
Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, SHA-256 tamper detection, 17 MC
It is a comprehensive resource hub compiling all LLM papers accepted at the International Conference on Learning Represe
One command. Full stack. Zero compromise. — All-in-one Claude Code skill with 33 modes, 6-layer security, 23 hooks, a
Kali Linux penetration testing skill for AI agents (Claude Code, OpenClaw, Hermes Agent). 200+ CLI tools, 15 scenario pl
Claude Skills for Governance, Risk, & Compliance (GRC): Expert-level compliance guidance for ISO 27001, SOC 2, FedRAMP,
Official companion repository for our survey "A Survey of the OpenClaw Ecosystem: From Platform Extensibility to Constra