Search

Security scanner for agent skill files - detects command injection, unsafe file operations, hardcoded secrets, and code injection risks

Security scanner for AI agent skills/plugins. Detects prompt injection, data exfiltration, excessive permissions, and supply chain attacks.

"Open-source toolkit (Python Library, Registry API, CLI) for secure, decentralized AI agent interoperability using A2A/MCP."

BSI/G7 SBOM-for-AI implementation — software, models, datasets, infrastructure, security, KPIs. With TIBET provenance + CBOM evidence linkage.

Security harness for AI coding agents (Claude Code, Codex CLI, etc.) — mitmproxy payload inspection + TOML policy control.

Secure multi-agent AI framework in Rust — WASM sandbox, 50+ skills, 14 LLM providers, agent intelligence, compliance modules

An AI assistant that executes pre-vetted scripts and tools instead of generating code from scratch. Reduces costs, eliminates hallucinations, and enhances security

Open-source autonomous AI assistant with 5-tier security, 62 tools, 14 LLM providers. Written in Rust. Single binary.

Skill vetting & supply chain security for OpenClaw. Scans SKILL.md files for prompt injection, credential theft, RCE, typosquatting, and social engineering.

Local-first security recon that briefs your AI coding agent: facts + tailored probe scripts, code-in / artifacts-out. No LLM, no server, no running app.

Technology-agnostic development template with multi-AI agent support (Cursor, Copilot, VSCode, Gemini), security-first patterns, and comprehensive testing guidelines

Agentic security detection & response harness — an LLM agent that investigates, authors, validates, and unit-tests Sigma detection rules offline, and documents findings in Notion.

Security skill installer for Claude Code, Gemini CLI, Cursor, Codex, and OpenCode. Patches vulnerabilities using a Red-Green-Refactor exploit-test protocol.

Drop-in security guardrails for AI agents. Blocks unauthorized tool calls, exfiltration, prompt injection, and secret leaks — in-process, sub-millisecond, zero network.

Ultimate MASTERMETA AI Agent System Installer - Production-ready CrewAI multi-agent framework with OWASP GenAI security, vector databases, and consciousness framework

Agent Identity Protocol - Zero-trust security layer for AI agents. Policy enforcement proxy for MCP with Human-in-the-Loop approval, DLP scanning, and audit logging.

AI coding agent powered by Doubao (豆包) via browser automation (doubao.com/chat/) — no API key needed. Performance-optimized. Enhanced with comprehensive security.

Security-first open-source coding agent with parallel tool execution, multimodal input, 4-tier permissions, audit trails, and 200+ LLM provider support

AI governance guardrails for coding agents. Framework-aligned security and compliance patterns from NIST AI RMF, OWASP Top 10 for LLMs, and ISO/IEC 42001.

Curated dataset of GenAI & agentic-AI security incidents mapped to OWASP LLM Top 10, OWASP Agentic Top 10, NIST AI RMF, and MITRE ATLAS.