EUVD-2025-198318

LangChain is a framework for building agents and LLM-powered applications. From versions 0.3.79 and prior and 1.0.0 to 1.0.6, a template injection vulnerability exists in LangChain's prompt template system that allows attackers to access Python object internals through template syntax. This...

CVE-2025-65106 LangChain Vulnerable to Template Injection via Attribute Access in Prompt Templates

LangChain is a framework for building agents and LLM-powered applications. From versions 0.3.79 and prior and 1.0.0 to 1.0.6, a template injection vulnerability exists in LangChain's prompt template system that allows attackers to access Python object internals through template syntax. This...

CVE-2025-65106

CVE-2025-65106 — LangChain template injection : LangChain versions 0.3.79 and earlier and 1.0.0 to 1.0.6 contain a template injection vulnerability in the prompt template system that allows access to Python object internals via template syntax, affecting ChatPromptTemplate and related classes whe...

CVE-2025-65106 LangChain Vulnerable to Template Injection via Attribute Access in Prompt Templates

LangChain is a framework for building agents and LLM-powered applications. From versions 0.3.79 and prior and 1.0.0 to 1.0.6, a template injection vulnerability exists in LangChain's prompt template system that allows attackers to access Python object internals through template syntax. This...

CVE-2025-62164

vLLM is an inference and serving engine for large language models LLMs. From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability could lead to a crash denial-of-service and potentially remote code execution RCE, exists in the Completions API endpoint. When processing user-supplied...

Beyond Jailbreak: Unveiling Risks in LLM Applications Arising from Blurred Capability Boundaries

LLM applications i.e., LLM apps leverage the powerful capabilities of LLMs to provide users with customized services, revolutionizing traditional application development. While the increasing prevalence of LLM-powered applications provides users with unprecedented convenience, it also brings fort...

CVE-2025-34330

AudioCodes Fax Server and Auto-Attendant IVR appliances versions up to and including 2.6.23 include a web administration component F2MAdmin that exposes an unauthenticated prompt upload endpoint at AudioCodesfiles/utils/IVR/diagram/ajaxPromptUploadFile.php. The script accepts an uploaded file and...

Out-of-bounds Write

Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Out-of-bounds Write via the todense function in the Completions API endpoint when processing user-supplied prompt embeddings. An attacker can achiev...

LangChain Vulnerable to Template Injection via Attribute Access in Prompt Templates

Context A template injection vulnerability exists in LangChain's prompt template system that allows attackers to access Python object internals through template syntax. This vulnerability affects applications that accept untrusted template strings not just template variables in ChatPromptTemplate...

GHSA-6QV9-48XG-FC7F LangChain Vulnerable to Template Injection via Attribute Access in Prompt Templates

Context A template injection vulnerability exists in LangChain's prompt template system that allows attackers to access Python object internals through template syntax. This vulnerability affects applications that accept untrusted template strings not just template variables in ChatPromptTemplate...

"To Survive, I Must Defect": Jailbreaking LLMs Via the Game-Theory Scenarios

As LLMs become more common, non-expert users can pose risks, prompting extensive research into jailbreak attacks. However, most existing black-box jailbreak attacks rely on hand-crafted heuristics or narrow search spaces, which limit scalability. Compared with prior attacks, we propose Game-Theor...

PT-2025-47809

Name of the Vulnerable Software and Affected Versions LangChain versions 0.3.79 and prior LangChain versions 1.0.0 through 1.0.6 Description LangChain is a framework used for building agents and applications powered by Large Language Models LLMs. A template injection issue exists in the prompt...

PT-2025-47648

Name of the Vulnerable Software and Affected Versions vLLM versions 0.10.2 through 0.11.0 Description vLLM is an inference and serving engine for large language models LLMs. A memory corruption issue exists in the Completions API endpoint, specifically when processing user-supplied prompt...

CVE-2025-34330

AudioCodes Fax Server and Auto-Attendant IVR appliances versions up to and including 2.6.23 include a web administration component F2MAdmin that exposes an unauthenticated prompt upload endpoint at AudioCodesfiles/utils/IVR/diagram/ajaxPromptUploadFile.php. The script accepts an uploaded file and...

CVE-2025-34330 AudioCodes Fax/IVR Appliance <= 2.6.23 Unauthenticated Prompt File Upload via ajaxPromptUploadFile.php

AudioCodes Fax Server and Auto-Attendant IVR appliances versions up to and including 2.6.23 include a web administration component F2MAdmin that exposes an unauthenticated prompt upload endpoint at AudioCodesfiles/utils/IVR/diagram/ajaxPromptUploadFile.php. The script accepts an uploaded file and...

CVE-2025-34330

The CVE-2025-34330 entry affects AudioCodes Fax Server and Auto-Attendant IVR appliances up to version 2.6.23. A web admin component (F2MAdmin) exposes an unauthenticated endpoint at AudioCodes_files/utils/IVR/diagram/ajaxPromptUploadFile.php that accepts uploaded files and writes them into C:\F2...

CVE-2025-34330 AudioCodes Fax/IVR Appliance <= 2.6.23 Unauthenticated Prompt File Upload via ajaxPromptUploadFile.php

AudioCodes Fax Server and Auto-Attendant IVR appliances versions up to and including 2.6.23 include a web administration component F2MAdmin that exposes an unauthenticated prompt upload endpoint at AudioCodesfiles/utils/IVR/diagram/ajaxPromptUploadFile.php. The script accepts an uploaded file and...

Cline Bot AI Agent Vulnerable to Data Theft and Code Execution

Mindgard reveals 4 critical security flaws in the popular Cline Bot AI coding agent. Learn how prompt injection can hijack the tool for API key theft and remote code execution...

Securing AI Agents against Prompt Injection Attacks

Retrieval-augmented generation RAG systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive benchmark for evaluating prompt injection risks in RAG-enabled A...

PT-2025-47479

AudioCodes Fax Server and Auto-Attendant IVR appliances versions up to and including 2.6.23 include a web administration component F2MAdmin that exposes an unauthenticated prompt upload endpoint at AudioCodes files/utils/IVR/diagram/ajaxPromptUploadFile.php. The script accepts an uploaded file an...