Security and IT operations teams that want to detect misuse of AI agents by placing decoy tools in their environment.
git clone https://github.com/beelzebub-labs/beelzebub.gitThird party software. By copying, downloading or installing it you accept the Academy legal notice: you are responsible for reviewing its code and permissions before use.
An open-source deception framework that lets you deploy decoy services and record how they are used. It can build decoy MCP tools that an agent would never call in normal work, so any use of them points to prompt injection or malicious agent behavior. Services and responses are defined in YAML.
Security and IT operations teams that want to detect misuse of AI agents by placing decoy tools in their environment. An open-source deception framework that lets you deploy decoy services and record how they are used. It can build decoy MCP tools that an agent would never call in normal work, so any use of them points to prompt injection or malicious agent behavior. Services and responses are defined in YAML.
Run this in your terminal: git clone https://github.com/beelzebub-labs/beelzebub.git
Yes. The code is on GitHub (beelzebub-labs/beelzebub) under the GPL-3.0 licence.
It passed our automatic scan for credential theft, hidden instructions and risky install commands. Third party open source software. Sabemos AI does not maintain it. Check the code and permissions before you connect it to company data.