4 RESULTS · “prompt-injection”
v0.10.2 · no license
Open-source adversary emulation for AI agents and MCP servers.
— · MIT
🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + CI ready.
v0.1.5 · MIT
Free MCP security scan: tool-poisoning & prompt-injection audit (OWASP LLM01/08) + trust badge
v0.5.0 · no license
A real inbox for AI agents: send, receive and thread email, behind a prompt-injection firewall.