augustus

Augustus - LLM 취약점 스캐너: 프롬프트 인젝션, 탈옥, 적대적 공격 테스트 Augustus - LLM 취약점 스캐너 프롬프트 인젝션, 탈옥, 인코딩 악용, 데이터 추출을 포함한 210개 이상의 적대적 공격으로 대규모 언어 모델을 테스트하세요. Augustus 는 보안 전문가를 위한 Go 기반 LLM 취약점 스캐너입니다. 광범위한 적대적 공격으로 대규모 언어 모델을 테스트하고, 28개 LLM 제공업체와 통합하며, 실행 가능한 취약점 보고서를 생성합니다. 연구 중심 도구와 달리 Augustus는 프로덕션 보안 테스트를...

vulnhuntr

LLM과 정적 코드 분석을 사용하여 원격으로 악용 가능한 취약점을 식별하는 도구입니다. 세계 최초로 자율 AI가 발견한 0데이 취약점 설명 Vulnhuntr은 LLM의 힘을 활용하여 원격 사용자 입력에서 시작하여 서버 출력으로 끝나는 전체 코드 호출 체인을 자동으로 생성 및 분석함으로써, 기존 정적 코드 분석 도구가 수행할 수 있는 범위를 훨씬 넘어서는 복잡하고 다단계이며 보안을 우회하는 취약점을 탐지합니다. 모든 0데이에 대한 Vulnhuntr 출력을 포함한 모든 세부 사항은 여기에서 확인하세요: Protect AI...

Automated Vulnerability Injection in Smart Contracts Using Large Language Models

Assessing vulnerability detection tools for smart contracts requires datasets with known ground truth, yet such datasets are scarce and difficult to build by hand. We propose an approach that uses Large Language Models LLMs to automatically inject vulnerabilities into Solidity smart contracts, an...

Awesome-LLMs-for-Vulnerability-Detection — Updated!

Awesome Large Language Models for Vulnerability Detection A curated list of papers, projects, and agent skills on using LLMs for vulnerability detection and discovery. 📄 Papers Only showing 2025 and later. For earlier work, see Papers Archive 2024 and earlier. Title| Venue| Year| Paper| Github...

Ai-Vulnerability-Code-Detector

AI-Powered Vulnerability Scanner A comprehensive security sca...

SecureAI-Scan v0.8.0

SecureAI-Scan The AI security scanner that proves its findings. SecureAI-Scan finds LLM, MCP, Agent Skill, and RAG vulnerabilities in TypeScript, JavaScript, and Python — and shows you the evidence: the exact source → flow → sink path for every dataflow finding, resolved through real imports, not...

augustus v0.14.15

Augustus - LLM vulnerability scanner for prompt injection, jailbreak, and adversarial attack testing Augustus - LLM Vulnerability Scanner Test large language models against 210+ adversarial attacks covering prompt injection, jailbreaks, encoding exploits, and data extraction. Augustus is a Go-bas...

SecureAI-Scan v0.7.0

SecureAI-Scan The AI security scanner that proves its findings. SecureAI-Scan finds LLM, MCP, Agent Skill, and RAG vulnerabilities in TypeScript, JavaScript, and Python — and shows you the evidence: the exact source → flow → sink path for every dataflow finding, resolved through real imports, not...

SecureAI-Scan v0.6.0

SecureAI-Scan The AI security scanner that proves its findings. SecureAI-Scan finds LLM, MCP, Agent Skill, and RAG vulnerabilities in TypeScript, JavaScript, and Python — and shows you the evidence: the exact source → flow → sink path for every dataflow finding, resolved through real imports, not...

CVE-2026-55514 vLLM denial of service via prompt embeds on M-RoPE models

vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is...

The Surface You Test Is Not the Surface That Breaks

Tool-augmented LLM agents are vulnerable to prompt injection: a third party who controls part of the agent's context can plant instructions that the agent then executes as if they came from the user. Current evaluations report a single attack success rate per model on one channel, the tool output...

CVE-2026-47102 LiteLLM < 1.83.10 Privilege Escalation via User Update

LiteLLM prior to 1.83.10 allows a user to modify their own userrole via the /user/update endpoint. While the endpoint correctly restricts users to updating only their own account, it does not restrict which fields may be changed. A user who can reach this endpoint can set their role to proxyadmin...

LiteLLM 安全漏洞

LiteLLM is an open-source application developed by Berri AI. It can utilize all LLM APIs in the OpenAI format. Prior to version 1.83.10, LiteLLM had a security vulnerability. This vulnerability stemmed from the lack of restrictions on the fields that could be modified by the /user and /update...

LiteLLM CVE-2026-42208 SQL Injection Exploited within 36 Hours of Disclosure

In yet another instance of threat actors quickly jumping on the exploitation bandwagon, a newly disclosed critical security flaw in BerriAI's LiteLLM Python package has come under active exploitation in the wild within 36 hours of the bug becoming public knowledge. The vulnerability, tracked as...

EUVD-2026-16478

vLLM has Hardcoded Trust Override in Model Files Enables RCE Despite Explicit User Opt-Out...

EUVD-2024-1292

Malicious code in bioql PyPI...

EUVD-2024-31707

Malicious code in bioql PyPI...

EUVD-2025-13062

Malicious code in bioql PyPI...

PT-2025-18649

Name of the Vulnerable Software and Affected Versions NVIDIA TensorRT-LLM affected versions not specified NVIDIA vGPU software affected versions not specified Description The issue concerns a data validation problem in the python executor of NVIDIA TensorRT-LLM, which can be exploited by an...

Spacy-LLM Server-Side Template Injection (SSTI) vulnerability

A Server-Side Template Injection SSTI vulnerability in Spacy-LLM v0.7.2 allows attackers to execute arbitrary code via injecting a crafted payload into the template field...