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, Tuesday 6 October 2026 · Retrospective · Covers 5 October 2026 00:00 to 6 October 2026 00:00 UTC

Read on the web

Top developments

MALFEX npm Malware Campaign: Three Payloads And An Adversary That Signs Their Work

Checkmarx · Incident · SCA

VA-26-278-01: Canimaan Software ClamXAV local privilege escalation

CISA · Advisory

Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge

arXiv · Research · Models

SCA

Backdooring Sparse Autoencoders

arXiv · Research · Models, SCA

Agentic SDLC

Correct Code, Broken Contributions? SWE-CC: Benchmarking Repository Policy Compliance for Coding Agents

arXiv · Research · Agentic SDLC, Trust

Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair

arXiv · Research · Agentic SDLC, Remediation

ReviewBench: An open benchmark for AI code review

GitHub · Analysis · Agentic SDLC

AI-BOM

How Much Assurance Does Your AI Supply Chain Need?

CoSAI · Analysis · AI-BOM, Trust

Remediation

New Dell System Update flaw lets hackers gain root privileges

BleepingComputer · Analysis · Remediation

Microsoft Exchange Flaw Lets Authenticated Attackers Read Other Users' Mailboxes

The Hacker News · Analysis · Remediation

Realtek Jungle SDK Exploit Attempts Deliver Cling Botnet With STUN-Based C2

The Hacker News · Analysis · Remediation

Trust

Can Power Draw Constrain Covert Compute? Limits of Analogue Verification for AI Governance

arXiv · Research · Trust

Efficient Auditing of Adversarial AI Agent Behavior from Agent Traces

arXiv · Research · Trust

ANT: A Multi-Granularity Network Traffic Dataset and Benchmark for Agents Behavior Auditing

arXiv · Research · Trust

Models

Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training

arXiv · Research · Models

Dynamic Budget Allocation for LLM Evaluation under Hard Resource Constraints

arXiv · Research · Models

Jailbreaking Open-Weight LLMs via Random Embedding Perturbations

arXiv · Research · Models

AI Security

MCP for agent-to-agent comms may be the riskiest protocol you've never heard of

Ars Technica: Security · Analysis · AI Security

Lineage-Aware Memory Governance: A Derivation-Gated Framework for Privacy-Preserving Column-Level Access Control in Enterprise AI Agents

arXiv · Research · AI Security

South Korea probes bank breaches amid suspected AI-powered attacks

BleepingComputer · Analysis · AI Security

Advisories in this window

  • 161 npm advisories · 132 critical · 14 high · 13 moderate · 2 low
  • 42 RubyGems advisories · 42 critical
  • 17 PyPI advisories · 3 critical · 7 high · 7 moderate
  • 4 crates.io advisories · 2 high · 2 moderate
  • 3 Multi-ecosystem advisories · 1 critical · 2 moderate
  • 2 Packagist advisories · 2 moderate
  • 2 Go 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.