PREVIEW. This is how it will look in an inbox; it was not sent to you. Each real email carries its own unsubscribe link and Keryn's postal address. KERYN HEADLINES Daily, Thursday 4 September 2025 Retrospective Covers 3 September 2025 00:00 to 4 September 2025 00:00 UTC Web: https://keryn.dev/headlines/daily/2025-09-04/ TOP DEVELOPMENTS [1] Google fixes actively exploited Android flaws in September update BleepingComputer · Incident · https://bleepingcomputer.com/news/security/google-fixes-actively-exploited-android-flaws-in-september-update [2] s1ngularity's Aftermath: AI, TTPs, and Impact in the Nx Supply Chain Attack Wiz · Incident · https://wiz.io/blog/s1ngularitys-aftermath [3] Indirect Prompt Injection Attacks Against LLM Assistants Schneier on Security · Incident · https://schneier.com/blog/archives/2025/09/indirect-prompt-injection-attacks-against-llm-assistants.html [4] Model Namespace Reuse: An AI Supply-Chain Attack Exploiting Model Name Trust Palo Alto Networks · Incident · https://unit42.paloaltonetworks.com/model-namespace-reuse [5] Malicious npm Packages Exploit Ethereum Smart Contracts to Target Crypto Developers The Hacker News · Research · https://thehackernews.com/2025/09/malicious-npm-packages-exploit-ethereum.html SAST [6] TraceLLM: Security Diagnosis Through Traces and Smart Contracts in Ethereum arXiv · Research · https://arxiv.org/abs/2509.03037 SCA [7] Salesloft Takes Drift Offline After OAuth Token Theft Hits Hundreds of Organizations The Hacker News · Analysis · https://thehackernews.com/2025/09/salesloft-takes-drift-offline-after.html REMEDIATION [8] VulnRepairEval: An Exploit-Based Evaluation Framework for Assessing Large Language Model Vulnerability Repair Capabilities arXiv · Research · https://arxiv.org/abs/2509.03331 TRUST [9] Constitutional Law and AI Governance: Constraints on Model Licensing and Research Classification arXiv · Research · https://arxiv.org/abs/2509.05361 MODELS [10] Prototype-Guided Robust Learning against Backdoor Attacks arXiv · Research · https://arxiv.org/abs/2509.08748 [11] Silent Until Sparse: Backdoor Attacks on Semi-Structured Sparsity arXiv · Research · https://arxiv.org/abs/2509.08747 [12] EverTracer: Hunting Stolen Large Language Models via Stealthy and Robust Probabilistic Fingerprint arXiv · Research · https://arxiv.org/abs/2509.03058 AI SECURITY [13] Hackers use new HexStrike-AI tool to rapidly exploit n-day flaws BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/hackers-use-new-hexstrike-ai-tool-to-rapidly-exploit-n-day-flaws ADVISORIES IN THIS WINDOW 7 Maven advisories · 2 critical · 4 moderate · 1 low 4 Packagist advisories · 3 moderate · 1 low 4 npm advisories · 2 high · 1 moderate · 1 low 1 PyPI advisory · 1 critical 1 crates.io advisory · 1 moderate All advisories: https://keryn.dev/headlines/advisories/ Titles, links and short excerpts only; every item links to its source. Preview: the unsubscribe link and Keryn's postal address are added to each email when it is sent.