LLAMATOR-Core/llamator
Red Teaming python-framework for testing chatbots and GenAI systems.
Provides modular attack vectors targeting prompt injection, jailbreaks, system prompt leakage, and resource exhaustion across LLMs, RAGs, and vision models. Supports multiple client integrations including LangChain, OpenAI-compatible APIs, and web interfaces (Selenium, Telethon), with extensible custom attack definitions. Generates detailed audit trails in Excel/CSV formats and DOCX test reports mapped to OWASP LLM vulnerability classifications.
201 stars and 275 monthly downloads. Available on PyPI.
Stars
201
Forks
20
Language
Python
License
—
Category
Last pushed
Jan 16, 2026
Monthly downloads
275
Commits (30d)
0
Dependencies
21
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/LLAMATOR-Core/llamator"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
sleeepeer/PoisonedRAG
[USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented...
JuliusHenke/autopentest
CLI enabling more autonomous black-box penetration tests using Large Language Models (LLMs)
kelkalot/simpleaudit
Allows to red-team your AI systems through adversarial probing. It is simple, effective, and...
SecurityClaw/SecurityClaw
A modular, skill-based autonomous Security Operations Center (SOC) agent that monitors...
AI-secure/AgentPoison
[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or...