196 matches found
ALPRs are recording your daily drive (Lock and Code S06E26)
This week on the Lock and Code podcast … There's an entire surveillance network popping up across the United States that has likely already captured your information, all for the non-suspicion of driving a car. Automated License Plate Readers, or ALPRs, are AI-powered cameras that scan and store ...
Understanding Security Risks of AI Agents' Dependency Updates
Package dependencies are a critical control point in modern software supply chains. Dependency changes can substantially alter a project's security posture. As AI coding agents increasingly modify software via pull requests, it is unclear whether their dependency decisions introduce distinct...
Prompt injection is a problem that may never be fixed, warns NCSC
Prompt injection is shaping up to be one of the most stubborn problems in AI security, and the UK’s National Cyber Security Centre NCSC has warned that it may never be “fixed” in the way SQL injection was. Two years ago, the NCSC said prompt injection might turn out to be the “SQL injection of th...
Securing the Model Context Protocol: Defending LLMs against Tool Poisoning and Adversarial Attacks
The Model Context Protocol MCP enables Large Language Models to integrate external tools through structured descriptors, increasing autonomy in decision-making, task execution, and multi-agent workflows. However, this autonomy creates a largely overlooked security gap. Existing defenses focus on...
EUVD-2025-200120
Portkey.ai Gateway: Server-Side Request Forgery SSRF in Custom Host...
A Wolf in Sheep's Clothing: Bypassing Commercial LLM Guardrails Via Harmless Prompt Weaving and Adaptive Tree Search
Large language models LLMs remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Existing approaches overwhelmingly operate within the prompt-optimization paradigm: whether through traditional algorithmic search or recent agent-based workflows, the...
Poems Can Trick AI Into Helping You Make a Nuclear Weapon
It turns out all the guardrails in the world won’t protect a chatbot from meter and rhyme...
Lack of Sufficient Guardrails Lead to Excessive Agency (LLM08) in Some LLM Applications
Overview Retell AI's API creates AI voice agents that have excessive permissions and functionality, as a result of insufficient amounts of guardrails. As a result, attackers can exploit this and conduct large scale social engineering, phishing, and misinformation campaigns. Description Retell AI...
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...
EchoGram Flaw Bypasses Guardrails in Major LLMs
HiddenLayer reveals the EchoGram vulnerability, which bypasses safety guardrails on GPT-5.1 and other major LLMs, giving security teams just a 3-month head start...
Black-Box Guardrail Reverse-Engineering Attack
Large language models LLMs increasingly employ guardrails to enforce ethical, legal, and application-specific constraints on their outputs. While effective at mitigating harmful responses, these guardrails introduce a new class of vulnerabilities by exposing observable decision patterns. In this...
Create Self-Improving AI Agents Using Spring AI Recursive Advisors
The Spring AI ChatClient offers a fluent API for communicating with an AI model. The fluent API provides methods for building the constituent parts of a prompt that gets passed to the AI model as input. Advisors are a key part of the fluent API that intercept, modify, and enhance AI-driven...
Prevalence of Security and Privacy Risk-Inducing Usage of AI-Based Conversational Agents
Recent improvement gains in large language models LLMs have lead to everyday usage of AI-based Conversational Agents CAs. At the same time, LLMs are vulnerable to an array of threats, including jailbreaks and, for example, causing remote code execution when fed specific inputs. As a result, users...
Atlas browser’s Omnibox opens up new privacy and security risks
It seems that with every new agentic browser we discover yet another way to abuse one. OpenAI recently introduced a ChatGPT based AI browser called Atlas. It didn’t take researchers long to find that the combined search and prompt bar—called the Omnibox—can be exploited. By pasting a specially...
A week in security (October 13 – October 19)
Last week on Malwarebytes Labs: Prosper data breach puts 17 million people at risk of identity theft Under the engineering hood: Why Malwarebytes chose WordPress as its CMS Video call app Huddle01 exposed 600K+ user logs Mango discloses data breach at third-party provider Roku accused of selling...
Breaking Guardrails, Facing Walls: Insights on Adversarial AI for Defenders and Researchers
Analyzing 500 CTF participants, this paper shows that while participants readily bypassed simple AI guardrails using common techniques, layered multi-step defenses still posed significant challenges, offering concrete insights for building safer AI systems...
Researchers break OpenAI guardrails
The maker of ChatGPT released a toolkit to help protect its AI from attack earlier this month. Almost immediately, someone broke it. On October 6, OpenAI ran an event called DevDay where it unveiled a raft of new tools and services for software programmers who use its products. As part of that, i...
OpenAI’s Guardrails Can Be Bypassed by Simple Prompt Injection Attack
Just weeks after its release, OpenAI’s Guardrails system was quickly bypassed by researchers. Read how simple prompt injection attacks fooled the system’s AI judges and exposed an ongoing security concern for OpenAI...