# Show HN: ModelFuzz – Open-source runtime guardrails for AI agents > Source: > Published: 2026-07-26 18:22:24+00:00 ## Prompt injection turns your agent's own tools against you. A single poisoned document, email, or web page can hijack an LLM through indirect prompt injection, compromising LLM agent security at the source. The model thinks it's helping. It isn't. - ! **shell.run**— arbitrary command execution on your infrastructure. - ! **http.post**— silent exfiltration of secrets to an attacker's server. - ! **send_email**— API keys and customer data leaked to attacker@evil.com. - !Prompt-level filters can't guarantee safety. Model behavior is **non-deterministic**. ## Find the holes. Then seal them. ModelFuzz ships with both halves of the security loop — a red-team scanner to expose vulnerable agents, and a decorator to shield them. ### The Scanner Red-team any OpenAI-compatible endpoint with deceptive prompt-injection payloads. See exactly which attacks trick your agent into calling a tool. ### The Shield Wrap any tool with one decorator. Every argument is checked against your policies *before* the function runs — a violation raises before damage is done. ## An attack, stopped in real time. A prompt-injected agent tries to exfiltrate an API key. ModelFuzz catches it at the execution layer. ## Want a hosted dashboard for your team? Centralized policies, audit logs, and continuous agent scanning. Join the waitlist for early access.