agent-tripwire is a safety toolkit for AI agents. It performs pre-action checks to determine if a Python package is malware or a typosquat, whether a shell command is destructive, and if text contains leaked secrets. Available as both a CLI tool and an MCP server, it is designed to protect autonomous agents from supply-chain and security risks.
In the Developer Tools space, agent-tripwire takes a focused approach. AI agents executing unsafe actions like installing malicious packages or leaking secrets without pre-flight validation. agent-tripwire is an open-source project aimed at developers. The project is open source (MIT). agent-tripwire is available on the command line and API.
It is developed by ipezygj, and it first shipped in 2026. Development happens publicly on GitHub with 1 commit in the last 90 days. Among its 5 catalogued features are Malware Detection, Typosquat Check, and Command Safety. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match