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 2 September 2026 · Retrospective · Covers 1 September 2026 00:00 to 2 September 2026 00:00 UTC

Read on the web

Top developments

Recently patched PaperCut zero-days used in data theft attacks

BleepingComputer · Advisory · Remediation

13 Malicious Packagist Packages Target Unpatched iPhones to Steal Crypto Wallet Seeds

The Hacker News · Research · SCA

Counterfeit installers to system compromise: Tracking a deceptive software download campaign

Microsoft · Incident

SAST

Towards Behavior Tree-Guided Vulnerability Detection with Lightweight LLMs

arXiv · Research · SAST

SCA

Linux Detection Engineering - Fileless Execution

Elastic · Analysis · SCA

The dark figure of supply chain detection

Aikido Security · Analysis · SCA

Agentic SDLC

Skill-as-API: Confidential Multi-Agent Coordination for Agentic Software Engineering

arXiv · Research · Agentic SDLC

Remediation

From Silicon to Boot Code: Extending Automated Program Repair to Firmware-Layer Security Workarounds

arXiv · Research · Remediation

Trust

Whistleblower says USPS deploying new, ‘untested’ IT systems governing mail-in ballots

CyberScoop · Analysis · Trust

Models

Adversarial Vulnerabilities of Neural Biomarker Identification Systems

arXiv · Research · Models

Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges

arXiv · Research · Models

HiveTraceGuard-Pro: A Compact Generative Guardrail for Prompt Injection, Jailbreaks, and Adversarial Obfuscation

arXiv · Research · AI Security, Models

AI Security

CoSAI Hosts Working Session on Open Delegation & Identity Standard (ODIS)

CoSAI · Standard / policy · AI Security

Agent Flight Recorder: Tamper-Evident Audit Trails with On-Chain Anchoring for Long-Horizon Tool-Using Agents

arXiv · Research · AI Security

What's in Your Agent's Context? Context Privilege Escalation Attacks against AI Agent Harness

arXiv · Research · AI Security

Advisories in this window

  • 51 npm advisories · 43 critical · 6 high · 2 moderate
  • 12 PyPI advisories · 3 critical · 2 high · 7 moderate
  • 10 Packagist advisories · 6 high · 3 moderate · 1 low
  • 1 Go advisory · 1 high
  • 1 Maven advisory · 1 high

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.