GuardionAI
GuardionAI is an Agent and MCP Security Gateway that provides unified security for AI agents and Model Context Protocol tools operating on enterprise data. It sits in the execution path to discover, redact sensitive data, enforce protection, and give teams visibility into actions that traditional SIEM, DLP, and identity layers cannot see. Every agent action is inspected, enforced, and logged at the protocol level across AI agents, LLM apps, RAG systems, chatbots, coding agents, MCP servers, internal tools, databases, operating systems, and cloud environments. GuardionAI protects against critical AI threats such as prompt injection, system override, web attacks, MCP tool poisoning, malicious code execution, NSFW content, PII and credential exposure, confidential data leakage, off-topic drift, and unauthorized access, mapped to OWASP LLM Top 10 and agentic AI threat frameworks. Its gateway provides four layers of protection.
Learn more
Muse Code
Muse Code is Meta’s terminal coding agent, powered by Muse Spark 1.2, for handling complex software engineering tasks across large repositories. The agent can plan changes, write code, validate results, and coordinate multiple persistent subagents during development sessions. Muse Code uses async background agents that stay active throughout a session to reduce repeated information gathering and help complete multi-step tasks with less steering. Its runtime uses a local event log that records model calls, tool runs, approvals, and edits so sessions can be replayed and resumed after failures. Muse Code includes bundled skills such as /plan for approval-gated planning, /grill for stress-testing plans, and /goal for working toward completion. Built for AI developers and software teams, Muse Code helps automate coding workflows, long-running engineering tasks, debugging, and repository-level development.
Learn more
ZeroLeaks
ZeroLeaks is an AI prompt security platform that helps organizations identify and fix exposed system prompts, internal tools, and logic vulnerabilities that could allow prompt injection, prompt extraction, or other forms of leakage that expose internal instructions or intellectual property to unauthorized actors. It provides an interactive dashboard where users can scan system prompts manually or automate scanning via CI/CD integration to catch leaks and injection vectors before code is deployed, and it uses an AI-powered red-team-style analysis engine to assess prompt surfaces for logic flaws, extraction risks, and potential misuse with evidence, scoring, and remediation recommendations. ZeroLeaks targets enterprise-grade security for large-language-model-based products by offering vulnerability assessments that highlight prompt exposure depth, prioritized risks, proof, and access paths for issues found, and suggested fixes such as prompt restructuring, tool gating, etc.
Learn more
AgentScan
AgentScan is a free, deterministic security scanner for AI agent skills. It checks a skill directory (Claude Code, Codex, OpenCode, MCP servers) for prompt injection, secrets, network calls, malware patterns, and obfuscation before you install it. Every finding has file:line evidence and a confidence score. It never runs the skill, never uploads anything, and works offline. Free and open source (MIT); Trust Pack adds 90 pre-audited skills via one command.
Learn more
