EUVD-2026-42976

Deloitte AI Assist for Customer exposed unauthenticated API endpoints that allowed an attacker with knowledge of additional parameters to read from or inject content into the retrieval-augmented generation RAG corpus. On 2026-03-25, AI Assist for Customer restricted network access and enforced...

CVE-2026-57476 Deloitte AI Assist for Customer unauthenticated RAG corpus read and write

Deloitte AI Assist for Customer exposed unauthenticated API endpoints that allowed an attacker with knowledge of additional parameters to read from or inject content into the retrieval-augmented generation RAG corpus. On 2026-03-25, AI Assist for Customer restricted network access and enforced...

CVE-2026-54602

FastGPT is a knowledge-based AI application platform. Prior to 4.15.0, GET /api/core/ai/record/getRecord authenticates the caller but loads LLM request and response traces only by requestId without team scoping, allowing any authenticated user to read another team's prompts, retrieved RAG chunks,...

CVE-2026-59098

LobeChat through 2.2.9 contains a broken access control vulnerability in the retrieval-augmented-generation semantic search functionality that allows authenticated attackers to access other users' data by exploiting missing user-identifier predicates in the chunk model semanticSearch method...

EUVD-2026-41429

LobeChat through 2.2.9 contains a broken access control vulnerability in the retrieval-augmented-generation semantic search functionality that allows authenticated attackers to access other users' data by exploiting missing user-identifier predicates in the chunk model semanticSearch method...

CVE-2026-59098 LobeChat 2.2.9 - Cross-User Document Disclosure via Unscoped RAG Semantic Search

LobeChat through 2.2.9 contains a broken access control vulnerability in the retrieval-augmented-generation semantic search functionality that allows authenticated attackers to access other users' data by exploiting missing user-identifier predicates in the chunk model semanticSearch method...

CVE-2026-59098 LobeChat 2.2.9 - Cross-User Document Disclosure via Unscoped RAG Semantic Search

LobeChat through 2.2.9 contains a broken access control vulnerability in the retrieval-augmented-generation semantic search functionality that allows authenticated attackers to access other users' data by exploiting missing user-identifier predicates in the chunk model semanticSearch method...

CVE-2026-59098 LobeChat 2.2.9 - Cross-User Document Disclosure via Unscoped RAG Semantic Search

LobeChat through 2.2.9 contains a broken access control vulnerability in the retrieval-augmented-generation semantic search functionality that allows authenticated attackers to access other users' data by exploiting missing user-identifier predicates in the chunk model semanticSearch method...

VeriChat: An Agentic Conversational AI Assistant for Hardware Security Verification

Hardware security verification is a multi-stage process in which engineers must navigate complex design analyses, threat considerations, and verification strategies. They often need security-focused guidance, yet current verification environments provide little structured support for such...

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG

Multimodal agentic retrieval-augmented generation RAG systems expand the attack surface beyond prompt injection to include text poisoning, image injection, direct-query attacks, and orchestrator-level tool manipulation. Existing red-teaming approaches are typically surface-specific and often...

Poisoned Playbooks: Demystifying Knowledge Poisoning Effects on AI Security Agents

AI security agents increasingly rely on Retrieval-Augmented Generation RAG to use external security knowledge for vulnerability analysis and exploit reasoning. This creates a new risk: poisoned write-ups can be operationalized into incorrect exploit behavior. Yet, prior work on RAG poisoning has...

Langflow: BaseFileComponent-based nodes arbitrary file read with RCE exploit

Summary All components based on BaseFileComponent are vulnerable to the following vulnerability: 1. Docling DoclingInlineComponent 2. Docling Serve DoclingRemoteComponent 3. Read File FileComponent 4. NVIDIA Retriever Extraction NvidiaIngestComponent 5. Video File VideoFileComponent 6. Unstructur...

A Layered Security Framework against Prompt Injection in RAG-Based Chatbots

Prompt injection is ranked as the most critical vulnerability in large language model LLM deployments by the OWASP Top 10 for LLM Applications, yet existing defenses operate at isolated pipeline stages and remain incomplete. Input filters cannot inspect retrieved documents, while output monitors...

OffSploit

OffSploit: Autonomous Exploit Adaptation & C2 Framework !Py...

Revisiting Vul-RAG: Reproducibility and Replicability of RAG-Based Vulnerability Detection with Open-Weight Models

Large language models LLMs have shown strong potential for automated software vulnerability detection, particularly in retrieval-augmented generation RAG settings. However, for approaches relying on proprietary models and APIs, reproducibility and replicability remain largely unexplored, raising...

R+R: Reassessing Java Security API Misuse in Current LLMs: A Replication on JCA and JSSE APIs with External Security Knowledge

The misuse of Java security APIs is a serious security problem in software development. Research in 2024 has shown that this problem is widespread in LLM-generated code. However, it remains unclear whether this phenomenon persists in current models and how external security knowledge affects it...

MaxKB 代码问题漏洞

MaxKB is an open-source question-answering system based on large language models and RAG, developed by 1Panel-dev. Versions of MaxKB prior to 2.8.1 contained code vulnerabilities. These vulnerabilities stemmed from a server-side request forgeing vulnerability in the OSS file service URL retrieval...

Intelligent Detection and Mitigation of Carpet-Bombing DDoS Attacks in SDN Using Retrieval-Augmented Generation and Large Language Models

Software-Defined Networking SDN provides flexible and programmable network management; however, its centralized control architecture remains highly vulnerable to Distributed Denial-of-Service DDoS attacks, particularly Carpet-Bombing DDoS attacks that distribute malicious traffic across multiple...

CVE-2026-21836 HCL DominoIQ is affected by broken access control

The HCL DominoIQ RAG feature is affected by a Broken Access Control vulnerability. Under certain circumstances, document level access restrictions will be ignored when determining what data to return from an AI query. This could enable an authenticated attacker to view sensitive data...

PT-2026-42166

Name of the Vulnerable Software and Affected Versions HCL DominoIQ affected versions not specified Description The RAG feature is affected by broken access control. Under certain circumstances, document level access restrictions are ignored when determining the data returned from an AI query, whi...