agentic_security
Agentic LLM Vulnerability Scanner / AI red teaming kit
Red-teaming your own agent workflows and LLM endpoints against jailbreaks, fuzzing and multimodal attacks before shipping them.
You want runtime protection; it is a scanner run against a target you supply credentials for, not a defence that sits in the request path.
About agentic_security
An open-source vulnerability scanner for Agent Workflows and Large Language Models (LLMs) Protecting AI systems from jailbreaks, fuzzing, and multimodal attacks. Explore the docs » · Report a Bug »
Agentic Security equips you with powerful tools to safeguard LLMs against emerging threats. Here's what you can do:
Where > will be replaced with the actual attack vector during the scan, insert the Bearer XXXXX header value with your app credentials.
agentic_security is listed in this index written primarily in Python, with 2.0k stars on GitHub. Its latest recorded repository push was in November 2026; that is not an ASE editorial review date.
pip install agentic_security