grendel-redteam is an open-source CLI tool designed for security researchers and developers to red-team AI agents. It simulates authorized attacks, such as prompt injection and jailbreaks, to evaluate the robustness of LLM and agent-based systems.
grendel-redteam sits in PulseGate's LLM eval & observability category. It focuses on testing and evaluating the security of AI agents against prompt injection and jailbreak attacks. It is built as an open-source project for AI security researchers and developers. The project is open source (Apache-2.0). grendel-redteam is available on the command line.
Behind grendel-redteam is alialtunar, and it first shipped in 2026. The project is developed in the open on GitHub with 24 commits in the last 90 days. Key capabilities include red-teaming, prompt injection testing, and jailbreak simulation.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do