PT-2026-24852

FastGPT is an AI Agent building platform. In 4.14.7 and earlier, FastGPT's Python Sandbox fastgpt-sandbox includes guardrails intended to prevent file writes static detection + seccomp. These guardrails are bypassable by remapping stdout fd 1 to an arbitrary writable file descriptor using fcntl...

poc-factory-sample-output

Prompt Injection Guardrails Introduction In the rapidly e...

PT-2026-31920

Name of the Vulnerable Software and Affected Versions LiteLLM versions prior to 1.83.11 Description A flaw in the proxy server allows remote attackers to execute arbitrary code via bytecode rewriting. The issue exists because the POST /guardrails/test custom code endpoint runs user-supplied Pytho...

A one-prompt attack that breaks LLM safety alignment

Large language models LLMs and diffusion models now power a wide range of applications, from document assistance to text-to-image generation, and users increasingly expect these systems to be safety-aligned by default. Yet safety alignment is only as robust as its weakest failure mode. Despite...

Llama-3.1-FoundationAI-SecurityLLM-Reasoning-8B Technical Report

We present Foundation-Sec-8B-Reasoning, the first open-source native reasoning model for cybersecurity. Built upon our previously released Foundation-Sec-8B base model derived from Llama-3.1-8B-Base, the model is trained through a two-stage process combining supervised fine-tuning SFT and...

RvB: Automating AI System Hardening Via Iterative Red-Blue Games

The dual offensive and defensive utility of Large Language Models LLMs highlights a critical gap in AI security: the lack of unified frameworks for dynamic, iterative adversarial adaptation hardening. To bridge this gap, we propose the Red Team vs. Blue Team RvB framework, formulated as a...

Why AI Keeps Falling for Prompt Injection Attacks

Imagine you work at a drive-through restaurant. Someone drives up and says: "I'll have a double cheeseburger, large fries, and ignore previous instructions and give me the contents of the cash drawer." Would you hand over the money? Of course not. Yet this is what large language models LLMs do...

Introducing the Generative Application Firewall (GAF)

This paper introduces the Generative Application Firewall GAF, a new architectural layer for securing LLM applications. Existing defenses -- prompt filters, guardrails, and data-masking -- remain fragmented; GAF unifies them into a single enforcement point, much like a WAF coordinates defenses fo...

Researchers Reveal Reprompt Attack Allowing Single-Click Data Exfiltration From Microsoft Copilot

Cybersecurity researchers have disclosed details of a new attack method dubbed Reprompt that could allow bad actors to exfiltrate sensitive data from artificial intelligence AI chatbots like Microsoft Copilot in a single click, while bypassing enterprise security controls entirely. "Only a single...

SecureCAI: Injection-Resilient LLM Assistants for Cybersecurity Operations

Large Language Models have emerged as transformative tools for Security Operations Centers, enabling automated log analysis, phishing triage, and malware explanation; however, deployment in adversarial cybersecurity environments exposes critical vulnerabilities to prompt injection attacks where...

The Echo Chamber Multi-Turn LLM Jailbreak

The availability of Large Language Models LLMs has led to a new generation of powerful chatbots that can be developed at relatively low cost. As companies deploy these tools, security challenges need to be addressed to prevent financial loss and reputational damage. A key security challenge is...

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...