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, Sunday 20 September 2026 Retrospective Covers 19 September 2026 00:00 to 20 September 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-09-20/ TOP DEVELOPMENTS [1] BragJack attacks hijack AI browser agents through malicious extensions BleepingComputer · Research · https://bleepingcomputer.com/news/security/bragjack-attacks-hijack-ai-browser-agents-through-malicious-extensions [2] SolarWinds Patches ARM Hard-Coded Key Flaw Enabling Unauthenticated RCE The Hacker News · Advisory · https://thehackernews.com/2026/09/solarwinds-patches-arm-hard-coded-key.html [3] Critical Pre-Auth RCE in Orkes Conductor Workflow Platform Exploited in the Wild The Hacker News · Incident · https://thehackernews.com/2026/09/critical-pre-auth-rce-in-orkes.html SAST [4] SoK: From Finding to Deployment: Systematizing the OS Kernel Bug Lifecycle arXiv · Research · https://arxiv.org/abs/2609.23218 SCA [5] CrowdSec Says TanStack npm Attack Led to Copy of 170 Private GitHub Repositories The Hacker News · Analysis · https://thehackernews.com/2026/09/crowdsec-says-tanstack-npm-attack-led.html DAST [6] From Capability to Assurance in Autonomous Penetration-Testing Harnesses: A Framework and Reference Implementation arXiv · Research · https://arxiv.org/abs/2609.22664 REMEDIATION [7] SelfOp: An Optimization Algorithm for Self-Improving Security Agents arXiv · Research · https://arxiv.org/abs/2609.22792 TRUST [8] When Agentic Trust Crosses Organizational Boundaries: Structural Externalization and a Reference Model for Trust Evidence arXiv · Research · https://arxiv.org/abs/2609.22961 [9] The Law of Stop: Interruptibility, Injunctions, and the Governance of Agentic AI arXiv · Research · https://arxiv.org/abs/2609.22882 [10] The Moral Check: Strategic AI Governance for the Pacing Problem arXiv · Research · https://arxiv.org/abs/2609.22869 MODELS [11] Trustworthy Agentic AI: Failure Modes, Mitigation Strategies, and a Lifecycle Framework for Autonomous LLM Systems arXiv · Research · https://arxiv.org/abs/2609.22712 [12] UBA-ORL: Unlearning-Activated Backdoor Attacks on Offline Reinforcement Learning arXiv · Research · https://arxiv.org/abs/2609.22711 AI SECURITY [13] Beyond Single-Model Injection: A Threat Model and Defense Architecture for Prompt Injection in Multi-Agent Systems arXiv · Research · https://arxiv.org/abs/2609.22949 [14] NostrAgent: A Decentralized Identity and Delegation Architecture for Sovereign Agentic Systems arXiv · Research · https://arxiv.org/abs/2609.22944 ADVISORIES IN THIS WINDOW 2 PyPI advisories · 2 critical 1 npm 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.