agixt (>=1.2.4, <=1.3.11), authx (0.9.1) +15 more potentially affected by CVE-2026-69248 via cryptography (41.0.0)

cryptography PYPI version 41.0.0 is affected by a known vulnerability. The following packages have a transitive dependency on cryptography and may be impacted: - agixt =1.2.4, =1.0.479, =1.3.5rc1, =1.0.0, =1.10.0, =2.0.0, =3.10.0rc1, =3.10.0rc1, =3.10.0rc1, =4.0.0a5 and more Source cves:...

agixt (>=1.2.4, <=1.3.11), authx (0.9.1) +15 more potentially affected by CVE-2026-69249 via cryptography (41.0.0)

cryptography PYPI version 41.0.0 is affected by a known vulnerability. The following packages have a transitive dependency on cryptography and may be impacted: - agixt =1.2.4, =1.0.479, =1.3.5rc1, =1.0.0, =1.10.0, =2.0.0, =3.10.0rc1, =3.10.0rc1, =3.10.0rc1, =4.0.0a5 and more Source cves:...

WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks

Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations. In these...

DiagChain: A Diagnostic Benchmark for Evaluating LLM Agents on Evidence-Grounded Attack Chain Reconstruction

Large Language Model LLM agents offer a promising approach to attack chain reconstruction by retrieving and interpreting heterogeneous telemetry to infer ordered attacker actions. However, existing benchmarks mainly evaluate final outputs or aggregate accuracy, providing limited insight into how...

The OpenAI Hack Shows the Genie Is Out of the Bottle

This essay originally appeared inForeign Policy. Earlier this month, two of OpenAI's models broke out of their containment sandbox and attacked another AI company. The story is kind of wild. OpenAI was running security tests on two of its models: GPT-5.6 Sol and an unreleased model that is almost...

delirium-ai-safety-benchmark — Updated!

Delirium AI Safety Benchmark A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion ACE and related liminal attack vectors. Delirium is not an exploitation tool. It is a standardized benchmark designed to detect the precise moment when a language model's attention...

Adversarial Attacks in Multi-Agent LLM Pipelines: Unveiling Structural Vulnerabilities in Agentic AI Architectures

Multi-agent LLM pipelines orchestrate multiple specialized language model agents into structured workflows where intermediate outputs are passed across agents to solve complex tasks. This design introduces a security gap absent in single-agent settings: once an agent accepts adversarial content, ...

Multi-LLM Consensus Framework for Evaluating Banking-Sector NIDS Dataset Coverage of MITRE ATT&CK Techniques

The systemic criticality of global banking networks has ren-dered them high-priority targets for advanced persistent threats, neces-sitating Network Intrusion Detection Systems NIDS whose operational effectiveness must extend beyond statistical accuracy. However, a signif-icant validation gap...

A Comparative Analysis of Automated Techniques for Security Bug Report Identification

Timely identification of security-related bug reports is essential to minimize the window of vulnerabilities in software systems. Manually screening incoming bug reports to identify security-related issues is time-consuming, error-prone, and non-scalable for large-scale software systems. Thus, a...

CoGate: Confidence-Gated Co-Decoding for Secure Code Generation

Large language models are widely used for code generation, but they can also produce insecure programs due to patterns learned from their pretraining data. Decoding-time steering has become an important solution to this problem: a small expert model is combined with the target model at each step ...

Piggybacking on Perception: Stealthy Concurrent Audio Prompt Injections against Multimodal LLM Agents

Large Language Model LLM-driven multimodal agents are increasingly deployed to execute autonomous tasks via continuous audio interaction. While this paradigm enhances interaction naturalness, it introduces a critical yet under-explored attack surface, as audio inputs inevitably contain...

Measuring the Tendency of AI Agents to Go Rogue

This essay was written with Barath Raghavan, and originally appeared inThe Guardian. In July, Hugging Face, a company that hosts much of the world's AI software and open-source AI models, was hacked. A malicious dataset had been used to run code on one of its servers. Whoever was behind it captur...

Measuring LLMs’ Ability to Perform Cryptanalysis

There's new benchmark measuring AI's ability to perform mathematical cryptanalysis. Anthropic's frontier model actually found new attacks. The benchmark: "CryptanalysisBench: Can LLMs do Cryptanalysis?" The idea is to benchmark the ability of LLMs to discover new mathematical cryptanalytic attack...

Open Security Benchmark: Towards Autonomous Enterprise Cyber Defense

Enterprises are moving toward autonomous cyber defense: agentic AI that builds situational awareness of an organization's security state and reasons from it to assessments, decisions, and actions. This rests on a holistic view of the enterprise's security state, the continuous, cross-vendor pictu...

PT-2026-65951

Aeon load time series segmentation benchmark Code Injection Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of aeon. User interaction is required to exploit this vulnerability in that the target must visit a...

MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair

Memory systems allow agents to retain and reuse information from past interactions, but they can also let malicious content persist. A malicious instruction crafted by an attacker may be stored in long-term memory, recalled much later, and quietly shape a real action. Recent benchmarks increasing...

HoF-Bench: Rediscovering Real AI-Discovered CVEs without Frontier Models

AISLE's analyzer is credited with more than 280 CVEs across 78 projects, including OpenSSL, curl, and GnuTLS. They introduce HoF-Bench named after AISLE's public Hall of Fame, a benchmark built from 95 of these public AI-discovered CVEs across eight repositories pinned at vulnerable commits...

SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents

Software engineering teams now deploy AI coding agents Cursor, Claude Code, GitHub Copilot as first-class productivity tools, installing domain-specific skill files to tailor agent behavior to project APIs, framework conventions, and organizational workflows. These complex Markdown files are easi...

StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents

Stealth, the discipline of achieving an objective without revealing your presence, capabilities, or collected intelligence, is what separates sophisticated operators from detectable ones. Elite security researchers and advanced persistent threats achieve their objectives unnoticed; autonomous...

A Controlled Candidate-Set Benchmark for Offline Satellite-Security Plan Decomposition

Some security-development settings require local models that map an objective to an ordered, checkable plan. We present a low-rank decomposition adapter and release a case-disjoint corpus with 24 authored decompositions and 83 derived next-step examples across 24 satellite-security cases. To...