Lucene search
+L

130 matches found

ATTACKERKB
ATTACKERKB
added 2026/03/30 3:51 p.m.4 views

CVE-2026-2286

CrewAI contains a server-side request forgery vulnerability that enables content acquisition from internal and cloud services, facilitated by the RAG search tools not properly validating URLs provided at runtime...

5.9AI score0.00467EPSS
SaveExploits0References2Affected Software1
Positive Technologies
Positive Technologies
added 2026/03/30 12:0 a.m.24 views

PT-2026-29050

Name of the Vulnerable Software and Affected Versions CrewAI affected versions not specified Description CrewAI contains a server-side request forgery condition that allows for the acquisition of content from internal and cloud services. This is facilitated by Retrieval-Augmented Generation RAG...

9.8CVSS5.9AI score0.00467EPSS
SaveExploits0References6
RedhatCVE
RedhatCVE
added 2026/03/28 4:56 a.m.9 views

CVE-2026-28788

Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to version 0.8.6, any authenticated user can overwrite any file's content by ID through the POST /api/v1/retrieval/process/files/batch endpoint. The endpoint performs no ownership check, so a...

7.1CVSS5.9AI score0.02858EPSS
SaveExploits1References1
Packet Storm News
Packet Storm News
added 2026/03/28 12:0 a.m.10 views

Red-MIRROR: Agentic LLM-Based Autonomous Penetration Testing with Reflective Verification and Knowledge-Augmented Interaction

Web applications remain the dominant attack surface in cybersecurity, where vulnerabilities such as SQL injection, XSS, and business logic flaws continue to cause significant data breaches. While penetration testing is effective for identifying these weaknesses, traditional manual approaches are...

6AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/03/26 12:0 a.m.7 views

PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems

Large Language Models LLMs have demonstrated remarkable performance across a wide range of applications. However, their practical deployment is often hindered by issues such as outdated knowledge and the tendency to generate hallucinations. To address these limitations, Retrieval-Augmented...

6AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/03/24 12:0 a.m.13 views

SoK: The Attack Surface of Agentic AI -- Tools, and Autonomy

Recent AI systems combine large language models with tools, external knowledge via retrieval-augmented generation RAG, and even autonomous multi-agent decision loops. This agentic AI paradigm greatly expands capabilities - but also vastly enlarges the attack surface. In this systematization, we m...

6.2AI score
SaveExploits0
Packet Storm News
Packet Storm News
added 2026/03/23 12:0 a.m.31 views

Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks

Retrieval-Augmented Generation RAG significantly mitigates the hallucinations and domain knowledge deficiency in large language models by incorporating external knowledge bases. However, the multi-module architecture of RAG introduces complex system-level security vulnerabilities. Guided by the R...

5.8AI score
SaveExploits0
CNNVD
CNNVD
added 2026/03/20 12:0 a.m.14 views

Langflow 安全漏洞

Langflow is an open-source visualization framework developed by Langflow for building multi-agent and RAG applications. Versions of Langflow prior to 1.9.0 contained a security vulnerability. This vulnerability stemmed from the deleteapikeyroute endpoint, which did not verify the ownership of the...

8.8CVSS5.9AI score0.0039EPSS
SaveExploits0References1
EUVD
EUVD
added 2026/03/18 12:31 p.m.13 views

EUVD-2026-12813

In LibreChat 0.8.1-rc2, a logged-in user obtains a JWT for both the LibreChat API and the RAG API...

6.3CVSS5.8AI score0.00232EPSS
SaveExploits1References3
EUVD
EUVD
added 2026/03/18 12:31 p.m.10 views

EUVD-2025-208825

LibreChat version 0.8.1-rc2 uses the same JWT secret for the user session mechanism and RAG API which compromises the service-level authentication of the RAG API...

8CVSS5.8AI score0.00344EPSS
SaveExploits1References3
ATTACKERKB
ATTACKERKB
added 2026/03/18 11:8 a.m.6 views

CVE-2025-41258

LibreChat version 0.8.1-rc2 uses the same JWT secret for the user session mechanism and RAG API which compromises the service-level authentication of the RAG API...

8CVSS5.8AI score0.00344EPSS
SaveExploits1References3
Vulnrichment
Vulnrichment
added 2026/03/18 11:8 a.m.8 views

CVE-2025-41258 LibreChat RAG API Authentication Bypass

LibreChat version 0.8.1-rc2 uses the same JWT secret for the user session mechanism and RAG API which compromises the service-level authentication of the RAG API...

8CVSS5.8AI score0.00344EPSS
SaveExploits1References2
Positive Technologies
Positive Technologies
added 2026/03/18 12:0 a.m.23 views

PT-2026-26053

🟠 CVE-2025-41258 - High LibreChat version 0.8.1-rc2 uses the same JWT secret for the user session mechanism and RAG API which compromises the service-level authentication of the RAG API. https://t.co/MJXOI2sVrJ https://t.co/WsKiIkw0M2...

8CVSS5.8AI score0.00344EPSS
SaveExploits1References6
EUVD
EUVD
added 2026/03/16 6:32 p.m.28 views

EUVD-2026-12454

LibreChat RAG API, version 0.7.0, contains a log-injection vulnerability that allows attackers to forge log entries...

5.8AI score0.00277EPSS
SaveExploits0References3
CNNVD
CNNVD
added 2026/03/16 12:0 a.m.22 views

LibreChat RAG API 安全漏洞

LibreChat RAG API is an open-source interface service for building retrieval-enhanced generation capabilities in LibreChat. Version 0.7.0 of the LibreChat RAG API contains a security vulnerability, which stems from log injection, potentially allowing attackers to forge log entries...

7.5CVSS6AI score0.00277EPSS
SaveExploits0References2
Packet Storm News
Packet Storm News
added 2026/03/05 12:0 a.m.11 views

SecureRAG-RTL: A Retrieval-Augmented, Multi-Agent, Zero-Shot LLM-Driven Framework for Hardware Vulnerability Detection

Large language models LLMs have shown remarkable capabilities in natural language processing tasks, yet their application in hardware security verification remains limited due to scarcity of publicly available hardware description language HDL datasets. This knowledge gap constrains LLM performan...

5.8AI score
SaveExploits0
GithubExploit
GithubExploit
added 2026/02/24 6:25 p.m.207 views

ai-security-toolkit

...

5.9AI score
SaveExploits0
Spring Security Advisories
Spring Security Advisories
added 2026/02/24 12:0 a.m.47 views

This Week in Spring - February 24th, 2026

Hi, Spring fans! Welcome to another awesome and oh-so-agentic week in Spring! We've got a ton to look into, and I've got even more to prepare for next week's DevNexus event in Atlanta, GA, so let's dive right into it! Be sure to say "hi" if you're going to be there, though! You've heard of Agent...

5.5AI score
SaveExploits0
EUVD
EUVD
added 2026/02/16 12:30 p.m.13 views

EUVD-2026-6091

A weakness has been identified in JeecgBoot 3.9.1. This vulnerability affects the function importDocumentFromZip of the file org/jeecg/modules/airag/llm/controller/AiragKnowledgeController.java of the component Retrieval-Augmented Generation. Executing a manipulation can lead to deserialization...

7.5CVSS5.1AI score0.00477EPSS
SaveExploits2References10
NVD
NVD
added 2026/02/16 12:16 p.m.9 views

CVE-2026-2555

A weakness has been identified in JeecgBoot 3.9.1. This vulnerability affects the function importDocumentFromZip of the file org/jeecg/modules/airag/llm/controller/AiragKnowledgeController.java of the component Retrieval-Augmented Generation. Executing a manipulation can lead to deserialization...

7.5CVSS0.0031EPSS
SaveExploits1References5
Rows per page
Query Builder