Security Scanner for Agent Skills
Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis, auto-fix.

Privacy Code Scanner and Dataflow Context Engine for AI coding agents
Offline security scanner for AI-agent repos, skills, plugins, and MCP servers.
Catch dangerous AI agent skills before they catch you. Zero-dependency security scanner for Agent Skills, SKILL.md and MCP configs.
The AI security agent guards your code.
Trivy plugin for starting an MCP server
Collection of agent skills to find vulnerabilities inside your web/mobile apps.
Scan any agent skill — authored or compiled — for prompt injection, secrets, and malicious execution before it touches your agent. Or compile the long tail on the fly.
Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)