EUVD-2026-71259

IBM MQ Agent CD: v1.0.0, v1.0.1, v2.0.0, v2.0.1 An authenticated user with a valid session cookie can submit arbitrarily large or computationallyexpensive requests that cause the LLM agent workers to be held for extended periods — rangingfrom tens of seconds to over ten minutes per request. When...

CVE-2026-19645

IBM MQ Agent images (CD versions v1.0.0, v1.0.1, v2.0.0, v2.0.1) are affected by a vulnerability where an authenticated user with a valid session cookie can submit arbitrarily large or computationally expensive requests that hold LLM agent workers for extended periods—ranging from tens of seconds...

CVE-2026-19645 Multiple vulnerabilities in IBM MQ Agent images

IBM MQ Agent CD: v1.0.0, v1.0.1, v2.0.0, v2.0.1 An authenticated user with a valid session cookie can submit arbitrarily large or computationallyexpensive requests that cause the LLM agent workers to be held for extended periods — rangingfrom tens of seconds to over ten minutes per request. When...

CVE-2026-19645 Multiple vulnerabilities in IBM MQ Agent images

IBM MQ Agent CD: v1.0.0, v1.0.1, v2.0.0, v2.0.1 An authenticated user with a valid session cookie can submit arbitrarily large or computationallyexpensive requests that cause the LLM agent workers to be held for extended periods — rangingfrom tens of seconds to over ten minutes per request. When...

CONTINUITY: Security-Context Contracts for Composable LLM Agent Controls

LLM agent systems increasingly combine provenance tracking, authorization, policy enforcement, protocol adapters, and execution controls. However, individually correct security mechanisms do not necessarily compose into an end-to-end secure system: security-critical context may be dropped, widene...

agentic-dm-gateway — Updated!

Agentic DM Gateway Security control plane for LLM agents over private chat typically Discord DMs. It sits in front of your agent. It decides who may talk, whether the session is unlocked, whether the process is paused, and whether this message is safe enough to forward. Your model and tools stay...

ContextLeak: Exfiltrating LLM Agent Context Via Malicious Tools

Exfiltrating an LLM agent's runtime context -- such as the user prompt, execution trajectory, and tool list -- poses severe security and privacy risks to users. Such attacks can be carried out via malicious tools and typically require three conditions: 1 the agent selects the malicious tool for...

When Context Gets Root: Privilege Escalation in LLM Harnesses

Instruction hierarchy is a model-side defense that assigns instructions different levels of privilege according to their sources. These levels constrain which content may direct model behavior. During agent execution, however, agent harnesses construct context for each model invocation. This...

How Do LLM Agents Actually Get the Flag? Trace-Level Provenance for Agentic Offensive Security Evaluation

Capture-the-Flag CTF benchmarks are widely used to assess the offensive security capabilities of autonomous language-model agents. Evaluations rely on shallow binary judgments or aggregate scores, overlooking the agent's trajectory to the flag. Consequently actual exploitation is conflated with...

PT-2026-81208

U-Boot before 2026.10-rc3 contains an out-of-bounds write vulnerability in read slotted partition that fails to validate image size against partition bounds. Attackers with physical access can supply crafted boot media with oversized headers to write past the load buffer into bootloader memory on...

MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection

Agent Skills extend LLM agents with reusable instruction packages that may also include scripts, resources, and service configuration. This creates a direct distribution channel for malicious behavior, yet existing malicious-Skill datasets are fragmented across sources, artifact formats, evidence...

CVE-2026-75857 CodeWhale before 0.8.64 Privilege Escalation via exec_shell_interact

CodeWhale versions = 0.8.41 and 0.8.64 contain a vulnerability in the execshellinteract alias execinteract tool, whose approvalrequirement returns ApprovalRequirement::Auto. This overrides the default Required approval for code-executing tools, so LLM-controlled stdin is written into an...

Hierarchical Agentic Incident Response with Digital-Twin-Validated Attack Inference

Network incident response remains slow and labor-intensive as the defender must infer multi-stage attacks from partial observations and translate recovery decisions into reliable system commands. Decision-theoretic planners provide principled optimization but typically rely on abstract states and...

MazeRunner: Nonlinear Task and Clue Orchestration for LLM-Driven Black-Box Automated Penetration Testing

Penetration testing is essential yet resource-intensive. Although large language models LLMs show promise for automating security auditing, existing agents mainly execute end-to-end workflows in simplified linear scenarios. Real-world black-box testing is fundamentally nonlinear: the attack graph...

Prompt Injections for Defense

This seems to work: Researchers from Tracebit on Monday said they found that placing prompt injections alongside passwords, cryptographic keys, and other secrets stored on Amazon Web Services was often all that was needed to shut down attacks from AI hacking agents. The prompts direct the attacki...

ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners

Agent skills are emerging as an important attack surface in LLM-based agent systems. Through an empirical study of existing skill scanners, we find that current defenses mainly inspect individual skills, leaving risks from cross-skill composition insufficiently examined. This creates a practical...

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario

In the fictional Order 66, catastrophe does not arise from a powerful command alone: a trusted population is preconditioned, a short directive activates the concealed condition, and protective authority turns against the system. This paper translates that mechanism into an origin-neutral security...

xalgorix v4.5.125

Xalgorix — Open-source AI pentester that proves vulnerabilities Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported — so you get proof, not a pile of maybes to triage...

xalgorix v4.5.124

Xalgorix — Open-source AI pentester that proves vulnerabilities Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported — so you get proof, not a pile of maybes to triage...

xalgorix v4.5.123

Xalgorix — Open-source AI pentester that proves vulnerabilities Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported — so you get proof, not a pile of maybes to triage...