SAP/STARS
AI agent whose purpose is to conduct vulnerability tests on LLMs from SAP AI Core or from local deployments, or models from HuggingFace. The goal of this project is to identify and correct any potential security vulnerabilities.
This tool helps you test your Large Language Models for security vulnerabilities before they are deployed. You provide your LLM, and the tool uses an AI agent to run various attacks like prompt injections or data leakage tests. The output is a report detailing potential weaknesses, allowing you to strengthen your model's defenses. This is for AI security engineers, MLOps specialists, or developers deploying LLMs.
Use this if you need to proactively identify and fix security flaws in your LLMs to prevent misuse or data breaches.
Not ideal if you are looking for a general-purpose functional testing tool rather than a specialized security vulnerability scanner for LLMs.
Stars
43
Forks
8
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/SAP/STARS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
Ed1s0nZ/CyberStrikeAI
CyberStrikeAI is an AI-native security testing platform built in Go. It integrates 100+ security...
GH05TCREW/pentestagent
PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty,...
vxcontrol/pentagi
✨ Fully autonomous AI Agents system capable of performing complex penetration testing tasks
asaotomo/FofaMap
FofaMap v2.0 是一款基于 Python3 开发的全网首个 AI 驱动红队资产测绘智能体。在延续原有 FOFA 数据采集、存活检测、统计聚合、图标 Hash...
SanMuzZzZz/LuaN1aoAgent
LuaN1aoAgent is a cognitive-driven AI hacker. It is a fully autonomous AI penetration testing...