Weekly Threat Intelligence Summary
Top 10 General Cyber Threats
Generated 2026-08-10T05:00:04.796002+00:00
- Russian State-Supported Cyber Actors Conduct Phishing Campaign Targeting Users of Zimbra Collaboration Suite (www.cisa.gov, 2026-07-21T19:08:02)
Score: 18.065
Russian State-Supported Cyber Actors Conduct Phishing Campaign Targeting Users of Zimbra Collaboration Suite Executive summary A group of Russian state-supported cyber actors has been targeting and compromising various Western government and commercial organizations using the Zimbra Collaboration Suite (ZCS) software since at least July 2025. The Russian state-supported advanced persistent threat (APT) group’s activity is tracked in the cybersecurity community under several names (see Cybersecur - Ransomware is the Scoreboard (www.recordedfuture.com, 2026-07-24T00:00:00)
Score: 7.832
Ransomware is the scoreboard for defensive architecture. Learn why traditional security methods fail and how to use AI and threat intelligence to identify and remediate critical attack paths. - Expanding AI Benchmarks in Cybersecurity Beyond Vulnerability Discovery (www.crowdstrike.com, 2026-08-06T05:00:00)
Score: 7.533 - July 2026 CVE Landscape (www.recordedfuture.com, 2026-08-07T00:00:00)
Score: 7.465
In July 2026, Insikt Group® identified 85 high-impact vulnerabilities that should be prioritized for remediation, 36 of which had a Very Critical Recorded Future Risk Score. This represents a 44% increase from last month. - Google’s synchronized passkeys can be stolen in ‘Pass‑ta‑key’ attacks (www.malwarebytes.com, 2026-08-05T11:11:48)
Score: 7.41
Over time, passkeys are supposed to replace passwords. But what happens when malware steals the master key? - Dealing with AI-Generated Extortion (www.recordedfuture.com, 2026-07-30T00:00:00)
Score: 7.332
Combat AI-generated extortion and fake ransomware leaks. Learn how organizations can verify data authenticity using robust governance and threat intelligence. - CrowdStrike 2026 Threat Hunting Report: Exploitation Window Closes as AI Use Accelerates (www.crowdstrike.com, 2026-08-03T05:00:00)
Score: 7.033 - Malwarebytes for Windows, now available on the Microsoft Store (www.malwarebytes.com, 2026-07-30T16:01:11)
Score: 6.443
Install Malwarebytes for Windows from the Microsoft Store with the same full protection and features. - AI chat bots are sliding into League of Legends friend requests (www.malwarebytes.com, 2026-08-07T21:26:41)
Score: 5.814
Chat bots are sending friend requests in Riot immediately after ending your game. What are the scammers up to now? - Meta ordered to pay $942 million over harm to children (www.malwarebytes.com, 2026-08-07T21:04:55)
Score: 5.812
A new court ruling not only fined Meta to the extent of $942 million but also ordered it to improve its age assurance tools.
Top 10 AI / LLM-Related Threats
Generated 2026-08-10T06:00:18.379125+00:00
- From Documentation to Zero-day Vulnerabilities: LLM-Driven Fuzzing of JavaScript Engines in PDF Readers (arxiv.org, 2026-08-10T04:00:00)
Score: 17.78
arXiv:2608.06641v1 Announce Type: new
Abstract: Existing fuzzers for PDF readers rely on simple test cases that involve only individual API calls, leading to limited coverage and potentially missing vulnerabilities that require sequences of API calls. To address these limitations, we propose PDFuzzer, a novel PDF engine fuzzer that automatically generates complex and meaningful API call sequences. PDFuzzer first uses a Large Language Model (LLM) to construct context-free grammars and infer the - On Seeding Watermarks to Detect Verbatim LLM Copy-Paste Responses (arxiv.org, 2026-08-10T04:00:00)
Score: 17.78
arXiv:2605.16336v2 Announce Type: replace
Abstract: Large language models (LLMs) have made fluent essay writing, code drafting, and quiz answering instantly available to students at every level, from secondary school through graduate study. Many educators do not object to LLM use \emph{per~se}; what they need to detect is the case in which a student pastes the assignment prompt into a chatbot and submits the model’s reply verbatim, without engaging with the work. Existing post-hoc AI-text - StepJack: Benchmarking Computer-Use Agent Safety Against Multi-Step Indirect Prompt Injection (arxiv.org, 2026-08-10T04:00:00)
Score: 17.48
arXiv:2608.06477v1 Announce Type: new
Abstract: Computer-use agents (CUAs) face a growing threat from indirect prompt injection, where adversarial instructions are planted in the environment such as web pages. In this paper, we introduce multi-step indirect prompt injection, a new attack class against CUAs in which the adversarial goal is decomposed into multiple innocuous-looking sub-steps and distributed across a chain of pages referenced along the agent’s navigation path. We develop a p - CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training (arxiv.org, 2026-08-10T04:00:00)
Score: 14.78
arXiv:2608.06471v1 Announce Type: new
Abstract: Despite recent advances, frontier large language model (LLM) agents remain limited in discovering and patching complex vulnerabilities in real-world software. Generally available agents can already aid attackers, who only need to find one exploitable weakness, while defenders must continuously identify and patch all vulnerabilities across fast-growing codebases. Stronger defensive agents would help close this gap, yet the scarcity of security trai - LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes (arxiv.org, 2026-08-10T04:00:00)
Score: 14.78
arXiv:2608.06795v1 Announce Type: new
Abstract: Low-rank adaptation (LoRA) enables efficient specialization and distribution of large language models through compact adapters. However, untrusted adapters introduce a supply-chain threat: a backdoored adapter can cause a model to generate harmful content, malicious code, political propaganda, or covert advertisements when an input contains a hidden trigger. Adapter-agnostic defenses merge the adapter with the base model, which dilutes backdoor si - Understanding and Improving Model Editing for Secure Code Generation (arxiv.org, 2026-08-10T04:00:00)
Score: 14.78
arXiv:2608.06848v1 Announce Type: new
Abstract: Large language models (LLMs) are widely used for code generation, yet they can reproduce vulnerable implementations learned from insecure training patterns. Prior work has mainly explored inference-time hardening, which reduces insecure generations without modifying the target model but relies on auxiliary components and adds runtime overhead. We conduct the first systematic study of model editing as a model-level hardening mechanism for secure co - When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse (arxiv.org, 2026-08-10T04:00:00)
Score: 14.78
arXiv:2608.06947v1 Announce Type: new
Abstract: Retrieval-augmented generation (RAG) is indispensable for enhancing large language models. However, RAGs are increasingly susceptible to poisoning attacks, in which adversarial documents are injected to manipulate generator outputs. Previous methods rely on output-side signals such as perplexity and consistency checks to detect such attacks. Nevertheless, our analysis reveals that deliberate attacks often induce false confidence, where poisoned ou - When Coordination Becomes a Threat: Communication Attacks in LLM-Controlled Multi-Robot Systems (arxiv.org, 2026-08-10T04:00:00)
Score: 14.78
arXiv:2608.06830v1 Announce Type: cross
Abstract: Large Language Models (LLMs) are increasingly used as high-level planners in embodied multi-robot systems, enabling robots to interpret natural language instructions and coordinate executable actions. Yet, this growing reliance on LLM planners also raises security concerns. Prior work has focused mainly on individual robots, while communication risks in multi-robot collaboration remain insufficiently understood. Existing multi-robot studies are - Statistical Analysis of Executability and Program Equivalence in Decompilation for IoT Vulnerability Detection (arxiv.org, 2026-08-10T04:00:00)
Score: 14.78
arXiv:2608.06960v1 Announce Type: cross
Abstract: Internet of Things (IoT) devices handle sensitive privacy-related information such as user audio, video, and authentication data, making it essential to detect vulnerabilities in their firmware. Decompilation, a key detection technique, has recently attracted attention because Large Language Models (LLMs) enable high readability and high recompilation success rates. However, because LLM outputs depend on probabilistic token prediction, they tend - WorldMark: A Plug-and-Play World Knowledge Interface for Cross-Host Language Model Watermarking (arxiv.org, 2026-08-10T04:00:00)
Score: 13.78
arXiv:2608.06416v1 Announce Type: new
Abstract: Watermarking traces the provenance of text produced by large language models by embedding statistically detectable signals during decoding. Existing schemes fall into logits-based, sampling-based, entropy-aware, and adaptive-strength families, yet all of them place watermark signals according to local token statistics. In the open-ended text-generation settings evaluated in this work, local statistics may provide insufficient guidance for placing - CyberLLM: A Multi-Agent LLM Framework for Autonomous Detection and Guarded Response in Automotive Cybersecurity (arxiv.org, 2026-08-10T04:00:00)
Score: 12.48
arXiv:2608.06651v1 Announce Type: new
Abstract: Software-Defined Vehicles (SDVs) expand the automotive attack surface across source code, runtime logs, and deployment topologies, while safety constraints forbid autonomous agents from acting without oversight. This paper presents CyberLLM, a multi-agent, LLM-orchestrated framework that autonomously detects vulnerabilities and executes remediations under a formal, runtime safety guard. Detection combines a deterministic layer (regex rules, AST an - Retrieval-Constrained Policy Optimization for Attack Technique Extraction from Cyber Threat Intelligence (arxiv.org, 2026-08-10T04:00:00)
Score: 12.48
arXiv:2608.06778v1 Announce Type: new
Abstract: Mapping cyber threat intelligence (CTI) text to MITRE ATT&CK techniques is essential for structured threat analysis, yet manual annotation is costly and does not scale. The ATT&CK taxonomy comprises several hundred attack techniques, and a single CTI passage may describe multiple techniques, making accurate and complete extraction challenging. Existing automated approaches fall short in different ways: multi-label classifiers struggle with - SoK: Cryptographic Key Recovery for Cryptoasset Custody and Financial Technologies (arxiv.org, 2026-08-10T04:00:00)
Score: 12.48
arXiv:2608.07104v1 Announce Type: new
Abstract: Cryptoasset systems often bind cryptographic key control to financial control: losing a wallet seed, custody share, hardware device, or smart-account credential can remove spend authority, while compromised recovery can enable theft. Existing work treats recovery through separate vocabularies–key backup, secret sharing, account recovery, credential re-issuance, social recovery, and asset migration–making mechanisms and tradeoffs difficult to com - Beyond Text Matching: Towards Reference-Free Evaluation for Human-Oriented Binary Reverse Engineering (arxiv.org, 2026-08-10T04:00:00)
Score: 12.48
arXiv:2608.07038v1 Announce Type: cross
Abstract: Human-Oriented Binary Reverse Engineering (HOBRE) aims to transform decompiled pseudocode into a more human-friendly representation, thereby reducing the cognitive burden of reverse analysis and improving efficiency. However, reliably evaluating HOBRE outputs remains a fundamental challenge: human evaluation is costly, time-consuming, and difficult to scale, while existing automated metrics either require executable test cases and runtime enviro - SynChain: Inducing Computer-Use Agent Systems to Construct Their Own Attack Chains (arxiv.org, 2026-08-10T04:00:00)
Score: 11.78
arXiv:2608.06862v1 Announce Type: new
Abstract: Computer-use agents~(CUAs) have transformed large language models into persistent execution systems capable of generating, storing, and reusing artifacts like skills and memory entries. However, existing security defenses largely treat attacks as externally triggered or temporally bounded, leaving a critical gap in addressing how compromise can propagate internally through an agent’s own persistent state. We reveal that malicious influence ca - Introducing Web Search on Amazon Bedrock for foundation model grounding (aws.amazon.com, 2026-08-04T18:39:14)
Score: 10.097
Today, we are introducing the general availability of Web Search on Amazon Bedrock. It is a server-side built-in tool that grounds model responses in current web knowledge. With Web Search, grounding becomes a native capability of Amazon Bedrock, with no third-party vendors to onboard, no external APIs to orchestrate, and no additional third party vendor security reviews to conduct. In this post, we walk through what Web Search on Amazon Bedrock is, why it matters, how to enable it using the Ope - Metasploit Framework 6.5 Released (www.rapid7.com, 2026-07-30T14:29:54)
Score: 9.965
Today we’re proud to announce that Metasploit Framework version 6.5 has been released. Over the past two years, with the help of countless contributors, we’ve added 422 new modules along with a whole slew of new features. Malleable C2 Profiles for HTTP One of the latest and most requested features is support for Malleable C2 profiles across all current Meterpreter payloads. This feature enables users to load a standard profile into Meterpreter and change the shape of its HTTP(S) traffic. All Met - LLM optimization integration for Amazon SageMaker Python SDK (aws.amazon.com, 2026-08-06T16:08:12)
Score: 9.548
The Amazon SageMaker Python SDK v3 now exposes generative AI inference recommendations in Amazon SageMaker AI directly in your notebook. Benchmark an endpoint, generate data-driven deployment recommendations, and deploy the recommended configuration without leaving your notebook workflow. - Rigid-Covert GNSS Spoofing of UAV Swarms: A Structural Blind Spot, Its Detection Limit, and Absolute-Anchor Defenses (arxiv.org, 2026-08-10T04:00:00)
Score: 9.48
arXiv:2608.06885v1 Announce Type: new
Abstract: Cooperative UAV-swarm defenses commonly cross-check GNSS positions against measured inter-drone geometry. We show that this relative-geometry channel has a structural blind spot: a common, slowly varying translation (a rigid-covert shift, RigidShift) preserves all pairwise distances and is therefore unobservable to any relative-only detector (a gauge-freedom argument). We validate this blindness on distance-verification and semidefinite-feasibilit - Casting the Net! Revisiting MasterFace Impersonation Attacks (arxiv.org, 2026-08-10T04:00:00)
Score: 9.48
arXiv:2608.06952v1 Announce Type: new
Abstract: Impersonation is a fundamental security threat in face recognition systems (FRSs). While the security of FRSs has been challenged by various attack vectors, under realistic adversarial capabilities, e.g., a limited number of decision-only authentication trials and no internal system knowledge, most attack techniques become infeasible. As a result, impersonation by zero-effort impostors, characterized by false match rate (FMR), is commonly regarded - The Ethics of Autonomous AI Agents for Offensive Security (arxiv.org, 2026-08-10T04:00:00)
Score: 9.48
arXiv:2607.20255v2 Announce Type: replace
Abstract: LLM-driven autonomous agents are reshaping offensive security. Unlike traditional penetration-testing tooling – deterministic, narrowly scoped, and operated by trained practitioners – agentic security tools exhibit indeterminacy along three independent dimensions. First, their actions are drawn from a non-deterministic policy whose outputs resist both ex-ante and ex-post explanation. This complicates incident attribution and pre-deployment saf - When Experience Becomes Instruction: Trajectory Poisoning in Self-Evolving Agent Skill Systems (arxiv.org, 2026-08-10T04:00:00)
Score: 9.48
arXiv:2608.05563v2 Announce Type: replace
Abstract: Self-evolving skill (SES) systems distill agent trajectories into persistent skills, allowing untrusted experience to become trusted instruction. We introduce PoisonedEvolution, a trajectory-poisoning attack on this promotion process. Our skill-visible black-box attacker can inspect a target skill and contribute bounded evidence, but cannot observe private pools or evolution logic or edit the skill bank. Artifact poisoning requires Inclusion, - Topological and Temporal Stability Analysis of the Lightning Network (arxiv.org, 2026-08-10T04:00:00)
Score: 9.48
arXiv:2512.20641v2 Announce Type: replace-cross
Abstract: The Lightning Network (LN) is the most prominent payment channel network built atop Bitcoin, designed to enable scalable, low-cost off-chain transactions. Understanding its structural evolution and temporal stability is critical for routing optimization, liquidity allocation, and infrastructure robustness. Leveraging a validated dataset of LN topology snapshots spanning 2019-2023, we compute a set of network-science metrics under directe - How legitimate cloud platforms enable phishers to bypass MFA (securelist.com, 2026-08-04T12:00:12)
Score: 9.131
We cover a cloud-based AitM attack scenario leveraging service workers and Ultraviolet, and provide detailed phishing hosting statistics across platforms like Cloudflare Workers, Vercel, Netlify, GitHub Pages, and IPFS. - ChainDrop: Inside a Self-Propagating npm Worm (unit42.paloaltonetworks.com, 2026-08-06T22:26:39)
Score: 9.011
Analysis of ChainDrop, an npm supply chain worm extracting GitHub Actions runner secrets and using Ethereum smart contracts for C2 routing. The post ChainDrop: Inside a Self-Propagating npm Worm appeared first on Unit 42 .
Auto-generated 2026-08-10
