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 4 March 2026 Retrospective Covers 3 March 2026 00:00 to 4 March 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-03-04/ TOP DEVELOPMENTS [1] CyberStrikeAI tool adopted by hackers for AI-powered attacks BleepingComputer · Research · https://bleepingcomputer.com/news/security/cyberstrikeai-tool-adopted-by-hackers-for-ai-powered-attacks [2] Fooling AI Agents: Web-Based Indirect Prompt Injection Observed in the Wild Palo Alto Networks · Research · https://unit42.paloaltonetworks.com/ai-agent-prompt-injection [3] CISA flags VMware Aria Operations RCE flaw as exploited in attacks BleepingComputer · Incident · https://bleepingcomputer.com/news/security/cisa-flags-vmware-aria-operations-rce-flaw-as-exploited-in-attacks SAST [4] Benchmark of Benchmarks: Unpacking Influence and Code Repository Quality in LLM Safety Benchmarks arXiv · Research · https://arxiv.org/abs/2603.04459 SCA [5] Human-Certified Module Repositories for the AI Age arXiv · Research · https://arxiv.org/abs/2603.02512 AGENTIC SDLC [6] Sharing is caring: Attestable and Trusted Workflows out of Distrustful Components arXiv · Research · https://arxiv.org/abs/2603.03403 [7] Join or host a GitHub Copilot Dev Days event near you GitHub · Analysis · https://github.blog/ai-and-ml/github-copilot/join-or-host-a-github-copilot-dev-days-event-near-you TRUST [8] The Controllability Trap: A Governance Framework for Military AI Agents arXiv · Research · https://arxiv.org/abs/2603.03515 [9] Shared (Mis)Understandings and the Governance of AI: A Thematic Analysis of the 2023-2024 Oversight of AI Hearings arXiv · Research · https://arxiv.org/abs/2603.03193 MODELS [10] Kraken: Higher-order EM Side-Channel Attacks on DNNs in Near and Far Field arXiv · Research · https://arxiv.org/abs/2603.02891 [11] DSBA: Dynamic Stealthy Backdoor Attack with Collaborative Optimization in Self-Supervised Learning arXiv · Research · https://arxiv.org/abs/2603.02849 [12] From Shallow to Deep: Pinning Semantic Intent via Causal GRPO arXiv · Research · https://arxiv.org/abs/2603.02675 AI SECURITY [13] Extending the Formalism and Theoretical Foundations of Cryptography to AI arXiv · Research · https://arxiv.org/abs/2603.02590 [14] Model Context Protocol SEP-2343: Clarify that elicitation requires authorization for remote servers Model Context Protocol · Proposal · https://github.com/modelcontextprotocol/modelcontextprotocol/pull/2343 ADVISORIES IN THIS WINDOW 206 npm advisories · 93 critical · 36 high · 69 moderate · 8 low 12 Packagist advisories · 4 critical · 1 high · 6 moderate · 1 low 8 Go advisories · 3 critical · 2 high · 3 moderate 7 PyPI advisories · 3 critical · 2 high · 2 moderate 4 crates.io advisories · 3 high · 1 low 2 Maven advisories · 1 critical · 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.