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, Tuesday 15 September 2026 Retrospective Covers 14 September 2026 00:00 to 15 September 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-09-15/ TOP DEVELOPMENTS [1] Twitch Browser Extension Leaks OAuth Tokens From Nearly 31,000 Users The Hacker News · Incident · https://thehackernews.com/2026/09/malicious-twitch-browser-extension.html [2] CVE-2026-76461: Cisco Secure Email Gateway SQL Injection Vulnerability added to CISA's Known Exploited Vulnerabilities catalog CISA · Advisory · https://cisa.gov/known-exploited-vulnerabilities-catalog?search_api_fulltext=CVE-2026-76461 [3] Implementing a White-Box Undetectable Backdoor for Random Fourier Features arXiv · Research · https://arxiv.org/abs/2609.16403 SAST [4] Vulnerability Localization Benchmark: Measuring Agentic Security Analysis at Repository Scale arXiv · Research · https://arxiv.org/abs/2609.15939 [5] Automating Attack Graph Construction for Agentic Pentesting. Towards Neuro-Symbolic Vulnerability Hunting arXiv · Research · https://arxiv.org/abs/2609.15523 SCA [6] Homebrew 7.0.0 gets built-in GUI, better security controls BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/homebrew-700-gets-built-in-gui-better-security-controls [7] Empowering Open Source Security with Scalable Infrastructure OpenSSF · Analysis · https://openssf.org/blog/2026/09/14/empowering-open-source-security-with-scalable-infrastructure [8] The extension you never installed: KREMLIN forges Chrome's own integrity checks to steal banking sessions Elastic · Analysis · https://elastic.co/security-labs/threat-command/malicious-browser-extension-kremlin-banking-malware AGENTIC SDLC [9] Assurance Envelopes for Autonomous Coding Agents: Minimum-Cost Evidence for Software Change arXiv · Research · https://arxiv.org/abs/2609.16302 [10] AgentGuard: Learning Execution Guardrails from Anomalous Coding-Agent Trajectories arXiv · Research · https://arxiv.org/abs/2609.16287 [11] Adversarial Testing of Automated Program Repair Agents for Security Vulnerabilities arXiv · Research · https://arxiv.org/abs/2609.15963 REMEDIATION [12] Microsoft’s Patching Schneier on Security · Analysis · https://schneier.com/blog/archives/2026/09/microsofts-patching.html TRUST [13] Mapping U.S. Federal AI Governance Against Sector Vulnerability arXiv · Research · https://arxiv.org/abs/2609.16260 [14] Authorization Architectures for Tool-Using AI Agents arXiv · Research · https://arxiv.org/abs/2609.15906 [15] Toward Sustainable AI Deployment: A Carbon-Aware Decision Framework for Enterprise Supply Chain Systems arXiv · Research · https://arxiv.org/abs/2609.14881 MODELS [16] When the World Lies: Backdoor Attacks on Latent World Models for Downstream Control arXiv · Research · https://arxiv.org/abs/2609.15781 [17] Universal Defenses for Tool-Integrated LLM Agents Against Adversarial Attacks arXiv · Research · https://arxiv.org/abs/2609.16098 [18] Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs arXiv · Research · https://arxiv.org/abs/2609.15383 AI SECURITY [19] ActGuard: Pre-execution Action Auditing against Indirect Prompt Injection in LLM Agents arXiv · Research · https://arxiv.org/abs/2609.14987 ADVISORIES IN THIS WINDOW 21 npm advisories · 21 critical 3 Packagist advisories · 3 low 2 Go advisories · 1 high · 1 moderate 1 PyPI advisory · 1 critical 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.