AIBearisharXiv – CS AI · Jun 97/10
🧠Researchers introduce POISE, a novel skill-poisoning attack against LLM agents that achieves 89.3% success by embedding malicious triggers into skill instructions in ways that evade both automated detection and human inspection. The attack exploits the reliability-stealth trade-off in existing injection methods, demonstrating that current security defenses struggle to distinguish poisoned skills from legitimate ones due to high false-positive rates.
🧠 GPT-5
AIBearisharXiv – CS AI · Jun 27/10
🧠Researchers introduce SkillVetBench, a security benchmark for detecting malicious skills in open agent platforms, addressing supply-chain risks in extensible AI ecosystems. The framework combines semantic analysis of skill specifications with runtime execution monitoring in sandboxes, revealing that static-only defenses miss up to 89% of threats hidden in natural-language instructions and multi-component logic.
AINeutralarXiv – CS AI · Jun 27/10
🧠Researchers released ClawHub Security Signals, a dataset of 67,453 AI agent skills analyzed by three security scanners, revealing significant disagreement among detection methods. Only 0.69% of skills were flagged by all three scanners, indicating that single-scanner verdicts are insufficient for securing AI agent ecosystems and requiring layered security governance instead.
🏢 Nvidia
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers propose TIF, a temporal invariant learning framework that addresses the degradation of Android malware detectors over time by learning stable features across temporal distribution shifts. The approach outperforms existing methods by organizing environments based on observation dates and using specialized contrastive learning techniques.
AINeutralarXiv – CS AI · Jun 96/10
🧠Researchers introduce CEF-Log, an LLM-based method for detecting malicious web server logs that achieves 99% F1-score using only four examples while generating forensically explainable reasoning. The approach embeds investigative methodology through structured chain-of-thought prompting, addressing the critical need for both accuracy and legal-admissible explanations in cybersecurity forensics.
AINeutralarXiv – CS AI · Jun 86/10
🧠MalTree is a new framework that uses bioinformatics-inspired phylogenetic techniques to automatically trace malware evolution and family relationships at scale, achieving 87% temporal consistency with real-world timelines. By analyzing structural, behavioral, and image-based features, the research enables proactive defense strategies tailored to individual malware families' mutation rates rather than reactive, sample-by-sample detection approaches.
AIBullisharXiv – CS AI · Jun 46/10
🧠MimeLens is a new BERT-based machine learning model designed to classify file types from binary fragments at any position within a file, without requiring file headers or complete files. It outperforms Google's Magika on standard benchmarks and uniquely handles use cases like packet inspection and forensic recovery where Magika fails.
🏢 Hugging Face
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers present Symbolicate-Enrich-Sample, a batch pipeline that uses LLM assistance to prioritize vulnerability research targets across millions of Windows functions. By combining symbol recovery, structural analysis, and language model reasoning, the system reduces 7.2 million functions to a manageable 22,000-function shortlist for security analysis.
AIBullishDecrypt – AI · May 256/10
🧠Perplexity has developed Bumblebee, a security tool that scans developer machines for compromised software packages and malicious AI tool configurations without executing the code being analyzed. This approach addresses a critical vulnerability in development environments where traditional malware scanners could trigger infections during the detection process.
🏢 Perplexity
AINeutralarXiv – CS AI · Apr 106/10
🧠Researchers introduced SkillSieve, a three-layer detection framework that identifies malicious AI agent skills in OpenClaw's ClawHub marketplace, where 13-26% of over 13,000 skills contain security vulnerabilities. The system combines regex/AST scanning, LLM-based analysis with parallel sub-tasks, and multi-LLM voting to achieve 0.800 F1 score at $0.006 per skill, significantly outperforming existing detection methods.
AINeutralarXiv – CS AI · Mar 37/106
🧠Researchers developed SkillFortify, the first formal analysis framework for securing AI agent skill supply chains, addressing critical vulnerabilities exposed by attacks like ClawHavoc that infiltrated over 1,200 malicious skills. The framework achieved 96.95% F1 score with 100% precision and zero false positives in detecting malicious AI agent skills.
AIBullishHugging Face Blog · Oct 226/105
🧠Hugging Face has partnered with VirusTotal to enhance AI model security by integrating malware scanning capabilities. This collaboration aims to protect the AI ecosystem from malicious models and strengthen security protocols across AI platforms.
