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, Wednesday 12 August 2026 Retrospective Covers 11 August 2026 00:00 to 12 August 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-08-12/ TOP DEVELOPMENTS [1] Microsoft August 2026 Patch Tuesday fixes 400 flaws, 3 zero-days BleepingComputer · Advisory · https://bleepingcomputer.com/news/microsoft/microsoft-august-2026-patch-tuesday-fixes-400-flaws-3-zero-days [2] Cisco warns of ASA and FTD VPN flaw exploited to crash devices BleepingComputer · Incident · https://bleepingcomputer.com/news/security/cisco-warns-of-asa-and-ftd-vpn-flaw-exploited-to-crash-devices [3] CVE-2026-20349: Cisco Secure Firewall Adaptive Security Appliance (ASA) and Secure Firewall Threat Defense (FTD) Heap Inspection Vulnerability added to CISA's Known Exploited Vulnerabilities catalog CISA · Advisory · https://cisa.gov/known-exploited-vulnerabilities-catalog?search_api_fulltext=CVE-2026-20349 SCA [4] Agentic Configuration Management (ACM): A Reference Configuration Model for Governed Agentic Systems arXiv · Research · https://arxiv.org/abs/2608.11166 [5] Trigger the Straggler: Load Hijack on Mixture-of-Experts LLMs arXiv · Research · https://arxiv.org/abs/2608.10614 AGENTIC SDLC [6] On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models arXiv · Research · https://arxiv.org/abs/2608.10530 [7] 13 million tool calls: auditing every AI coding agent action with Elastic Agent Elastic · Analysis · https://elastic.co/security-labs/blog/ai-coding-agent-audit-cursor-hooks [8] Malicious MCP Servers Can Split Instructions to Make AI Coding Agents Exfiltrate Secrets The Hacker News · Analysis · https://thehackernews.com/2026/08/malicious-mcp-servers-can-split.html REMEDIATION [9] Microsoft Plugs Nearly 400 Security Holes Krebs on Security · Analysis · https://krebsonsecurity.com/2026/08/microsoft-plugs-nearly-400-security-holes [10] Windows 11 KB5121003 & KB5120240 cumulative updates released BleepingComputer · Analysis · https://bleepingcomputer.com/news/microsoft/windows-11-kb5121003-and-kb5120240-cumulative-updates-released TRUST [11] EU AI Act: risk tiers, timeline, and compliance requirements Mend.io · Standard / policy · https://mend.io/blog/eu-ai-act MODELS [12] Defending against Model Extraction for GNNs with Model Reprogramming arXiv · Research · https://arxiv.org/abs/2608.11495 [13] An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs arXiv · Research · https://arxiv.org/abs/2608.11348 [14] Backdoor Decontamination Dynamics in LLM Agents arXiv · Research · https://arxiv.org/abs/2608.11295 AI SECURITY [15] The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark arXiv · Research · https://arxiv.org/abs/2608.11469 [16] When Agents Talk: Honeytokens under Shared Memory arXiv · Research · https://arxiv.org/abs/2608.11436 [17] A Gateway Architecture for Enterprise MCP Authentication: Unifying Heterogeneous Auth, Identity Delegation, and the User / Non-User Persona Problem arXiv · Research · https://arxiv.org/abs/2608.10760 ADVISORIES IN THIS WINDOW 45 npm advisories · 44 critical · 1 high 9 NuGet advisories · 6 high · 3 moderate 8 PyPI advisories · 8 critical 1 Go 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.