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, Friday 5 June 2026 · Retrospective · Covers 4 June 2026 00:00 to 5 June 2026 00:00 UTC

Read on the web

Top developments

Hola Browser for Windows compromised to deliver cryptominer

BleepingComputer · Incident · SCA

Claude Code GitHub Action Flaw Let One Malicious Issue Hijack Repositories

The Hacker News · Incident · Agentic SDLC, AI Security

Credit card theft campaign abuses Stripe to host stolen payment info

BleepingComputer · Incident

SAST

AttackPathGNN: Cross-function vulnerability detection in smart contracts using state interference graphs and conjunction pooling

arXiv · Research · SAST

DAST

ZERO-APT: A Closed-Loop Adversarial Framework for LLM-Driven Automated Penetration Testing under Intelligent Defense

arXiv · Research · DAST, Trust

Agentic SDLC

Microskill Architecture: A Modular Skill-Driven Framework for AI-Native Code Generation

arXiv · Research · Agentic SDLC

SmellBench: Towards Fine-Grained Evaluation of Code Agents on Refactoring Tasks

arXiv · Research · Agentic SDLC

Remediation

Cisco warns of critical Unified CM flaw with PoC exploit code

BleepingComputer · Analysis · Remediation

Trust

Revisiting Sustainability by Design in AI Protocol Governance: An Empirical Review of Comparative DAO and Corporate-Led Standards for the SDGs

arXiv · Research · Trust

Models

Steering Vectors are an Adversarial Attack Surface

arXiv · Research · Models

Consistency Training Along the Transformer Stack

arXiv · Research · Models

Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense

arXiv · Research · Models

AI Security

WebMCP Tool Surface Poisoning: Runtime Manipulation Attacks on LLM Agents

arXiv · Research · AI Security

GuardNet: Ensemble Strategies of Shallow Neural Networks for Robust Prompt Injection and Jailbreak Detection

arXiv · Research · AI Security, Models

ThreatsDay Bulletin: AI Agents Gone Wrong, Sketchy C2 Tools, ClickFix Tricks, JS Backdoors & 20+ New Stories

The Hacker News · Analysis · AI Security

Advisories in this window

  • 18 PyPI advisories · 2 critical · 1 high · 6 moderate · 9 low
  • 14 Packagist advisories · 1 critical · 1 high · 11 moderate · 1 low
  • 10 npm advisories · 3 critical · 2 high · 4 moderate · 1 low
  • 7 Go advisories · 2 high · 4 moderate · 1 low
  • 2 RubyGems advisories · 2 moderate
  • 2 Maven advisories · 1 critical · 1 moderate
  • 2 crates.io advisories · 2 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.