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

Read on the web

Top developments

CyberStrikeAI tool adopted by hackers for AI-powered attacks

BleepingComputer · Research · AI Security

Fooling AI Agents: Web-Based Indirect Prompt Injection Observed in the Wild

Palo Alto Networks · Research · AI Security

CISA flags VMware Aria Operations RCE flaw as exploited in attacks

BleepingComputer · Incident

SAST

Benchmark of Benchmarks: Unpacking Influence and Code Repository Quality in LLM Safety Benchmarks

arXiv · Research · AI Security, Models, SAST

SCA

Human-Certified Module Repositories for the AI Age

arXiv · Research · SCA

Agentic SDLC

Sharing is caring: Attestable and Trusted Workflows out of Distrustful Components

arXiv · Research · Agentic SDLC

Join or host a GitHub Copilot Dev Days event near you

GitHub · Analysis · Agentic SDLC

Trust

The Controllability Trap: A Governance Framework for Military AI Agents

arXiv · Research · Trust

Shared (Mis)Understandings and the Governance of AI: A Thematic Analysis of the 2023-2024 Oversight of AI Hearings

arXiv · Research · Trust

Models

Kraken: Higher-order EM Side-Channel Attacks on DNNs in Near and Far Field

arXiv · Research · Models

DSBA: Dynamic Stealthy Backdoor Attack with Collaborative Optimization in Self-Supervised Learning

arXiv · Research · Models

From Shallow to Deep: Pinning Semantic Intent via Causal GRPO

arXiv · Research · Models

AI Security

Extending the Formalism and Theoretical Foundations of Cryptography to AI

arXiv · Research · AI Security, Models

Model Context Protocol SEP-2343: Clarify that elicitation requires authorization for remote servers

Model Context Protocol · Proposal · AI Security

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

Titles, links and short excerpts only; every item links to its source. Selection is automatic; the editor's note is AI-drafted and checked as described. Preview: the unsubscribe link and Keryn's postal address are added to each email when it is sent.