Design Patterns for Securing LLM Agents against Prompt Injections

As AI agents powered by Large Language Models LLMs become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge. Among the most pressing threats are prompt injection attacks, which exploit the agent's resilience on...

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods

In this work, we show that some machine unlearning methods may fail when subjected to straightforward prompt attacks. We systematically evaluate eight unlearning techniques across three model families, and employ output-based, logit-based, and probe analysis to determine to what extent supposedly...

LLMs Cannot Reliably Judge (Yet?): a Comprehensive Assessment on the Robustness of LLM-As-A-Judge

Large Language Models LLMs have demonstrated remarkable intelligence across various tasks, which has inspired the development and widespread adoption of LLM-as-a-Judge systems for automated model testing, such as red teaming and benchmarking. However, these systems are susceptible to adversarial...

Securing Generative AI Agentic Workflows: Risks, Mitigation, and a Proposed Firewall Architecture

Generative Artificial Intelligence GenAI presents significant advancements but also introduces novel security challenges, particularly within agentic workflows where AI agents operate autonomously. These risks escalate in multi-agent systems due to increased interaction complexity. This paper...

Evaluation Empirique De La Sécurisation Et De L'Alignement De ChatGPT Et Gemini: Analyse Comparative Des Vulnérabilités Par Expérimentations De Jailbreaks

Large Language models LLMs are transforming digital usage, particularly in text generation, image creation, information retrieval and code development. ChatGPT, launched by OpenAI in November 2022, quickly became a reference, prompting the emergence of competitors such as Google's Gemini. However...

DAVSP: Safety Alignment for Large Vision-Language Models Via Deep Aligned Visual Safety Prompt

Large Vision-Language Models LVLMs have achieved impressive progress across various applications but remain vulnerable to malicious queries that exploit the visual modality. Existing alignment approaches typically fail to resist malicious queries while preserving utility on benign ones effectivel...

CVE-2025-49619: Improper Neutralization of Special Elements Used in a Template Engine

Skyvern through 0.1.85 is vulnerable to server-side template injection SSTI in the Prompt field of workflow blocks such as the Navigation v2 Block. Improper sanitization of Jinja2 template input allows authenticated users to inject crafted expressions that are evaluated on the server, leading to...

CVE-2025-49619

Skyvern through 0.1.85 is vulnerable to server-side template injection SSTI in the Prompt field of workflow blocks such as the Navigation v2 Block. Improper sanitization of Jinja2 template input allows authenticated users to inject crafted expressions that are evaluated on the server, leading to...

Stealix: Model Stealing Via Prompt Evolution

Model stealing poses a significant security risk in machine learning by enabling attackers to replicate a black-box model without access to its training data, thus jeopardizing intellectual property and exposing sensitive information. Recent methods that use pre-trained diffusion models for data...

Sentinel: SOTA Model to Protect against Prompt Injections

Large Language Models LLMs are increasingly powerful but remain vulnerable to prompt injection attacks, where malicious inputs cause the model to deviate from its intended instructions. This paper introduces Sentinel, a novel detection model, qualifire/prompt-injection-sentinel, based on the...

CLSA-2025-1748945064 Fix CVE(s): CVE-2019-10206, CVE-2019-14856

SECURITY UPDATE: password prompt vulnerability from template expansion - debian/patches/CVE-2019-10206.patch: prevent templating of passwords from prompt to avoid special characters triggering it incorrectly - CVE-2019-10206 - debian/patches/CVE-2019-14856.patch: fix incomplete CVE-2019-10206 pat...

VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents

Computer-Use Agents CUAs with full system access enable powerful task automation but pose significant security and privacy risks due to their ability to manipulate files, access user data, and execute arbitrary commands. While prior work has focused on browser-based agents and HTML-level attacks,...

ATAG: AI-Agent Application Threat Assessment with Attack Graphs

Evaluating the security of multi-agent systems MASs powered by large language models LLMs is challenging, primarily because of the systems' complex internal dynamics and the evolving nature of LLM vulnerabilities. Traditional attack graph AG methods often lack the specific capabilities to model...

Timing Side-channel Attacks

vllm is vulnerable to Timing side-channel attacks. The vulnerability is due to timing discrepancies during the prefill phase by the PageAttention mechanism reusing matching prefix chunks, which speeds up token generation and allows an attacker to infer prompt similarity or presence...

Browser is prompted to install Citrix Workspace lite.

Receiving prompt to install Citrix Workspace lite when accessing store URL When accessing workspace we see that as Citrix workspace lite However, the installed app is Citrix Workspace app...

Security Concerns for Large Language Models: a Survey

Large Language Models LLMs such as GPT-4 and its recent iterations, Google's Gemini, Anthropic's Claude 3 models, and xAI's Grok have caused a revolution in natural language processing, but their capabilities also introduce new security vulnerabilities. In this survey, we provide a comprehensive...

SafeGenes: Evaluating the Adversarial Robustness of Genomic Foundation Models

Genomic Foundation Models GFMs, such as Evolutionary Scale Modeling ESM, have demonstrated significant success in variant effect prediction. However, their adversarial robustness remains largely unexplored. To address this gap, we propose SafeGenes: a framework for Secure analysis of genomic...

Adversarial Threat Vectors and Risk Mitigation for Retrieval-Augmented Generation Systems

Retrieval-Augmented Generation RAG systems, which integrate Large Language Models LLMs with external knowledge sources, are vulnerable to a range of adversarial attack vectors. This paper examines the importance of RAG systems through recent industry adoption trends and identifies the prominent...

fastmonai (>=0.3.6, <=0.8.3), melotts-krqnf (0.1.2) +4 more potentially affected by CVE-2025-48889 via gradio (3.36.1)

gradio PYPI version 3.36.1 is affected by a known vulnerability. The following packages have a transitive dependency on gradio and may be impacted: - fastmonai =0.3.6, =2.1.0, =1.2.2, =0.0.4, =0.0.5 Source cves: CVE-2025-48889 Source advisory: OSV:GHSA-8JW3-6X8J-V96G...

CVE-2025-5276

Versions of the package mcp-markdownify-server before 1.0.0 are vulnerable to Server-Side Request Forgery SSRF via the Markdownify.get function. An attacker can craft a prompt that, once accessed by the MCP host, can invoke the webpage-to-markdown, bing-search-to-markdown, and youtube-to-markdown...