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

Weekly, week 1 of 2026 · Retrospective · Covers 23 December 2025 12:00 to 30 December 2025 12:00 UTC

Read on the web

Top developments

Strengthening supply chain security: Preparing for the next malware campaign

GitHub · Incident · Trust

27 Malicious npm Packages Used as Phishing Infrastructure to Steal Login Credentials

The Hacker News · Research · SCA

MongoBleed (CVE-2025-14847) exploited in the wild: everything you need to know

Wiz · Incident

SCA

Trust Wallet says 2,596 wallets drained in $7 million crypto theft attack

BleepingComputer · Analysis · SCA

Agentic AI for Autonomous Defense in Software Supply Chain Security: Beyond Provenance to Vulnerability Mitigation

arXiv · Research · AI Security, SCA, Trust

Fake MAS Windows activation domain used to spread PowerShell malware

BleepingComputer · Analysis · SCA

CoTDeceptor:Adversarial Code Obfuscation Against CoT-Enhanced LLM Code Agents

arXiv · Research · Agentic SDLC, SCA

DAST

GoldenFuzz: Generative Golden Reference Hardware Fuzzing

arXiv · Research · DAST

Future of DAST: Why AI-Generated Code Demands a New Strategy

Checkmarx · Analysis · DAST

Remediation

Rethinking the Capability of Fine-Tuned Language Models for Automated Vulnerability Repair

arXiv · Research · Models, Remediation

MongoDB warns admins to patch severe vulnerability immediately

BleepingComputer · Analysis · Remediation

Trust

Adaptive Trust Consensus for Blockchain IoT: Comparing RL, DRL, and MARL Against Naive, Collusive, Adaptive, Byzantine, and Sleeper Attacks

arXiv · Research · Models, Trust

Toward Secure and Compliant AI: Organizational Standards and Protocols for NLP Model Lifecycle Management

arXiv · Research · Trust

A Blockchain-Monitored Agentic AI Architecture for Trusted Perception-Reasoning-Action Pipelines

arXiv · Research · Trust

Operationalizing the CoSAI Risk Map (CoSAI-RM)

CoSAI · Analysis · Trust

Models

Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?

arXiv · Research · Models

DivQAT: Enhancing Robustness of Quantized Convolutional Neural Networks against Model Extraction Attacks

arXiv · Research · Models

Multilingual Hidden Prompt Injection Attacks on LLM-Based Academic Reviewing

arXiv · Research · AI Security, Models

EquaCode: A Multi-Strategy Jailbreak Approach for Large Language Models via Equation Solving and Code Completion

arXiv · Research · Models

AI Security

Toward Trustworthy Agentic AI: A Multimodal Framework for Preventing Prompt Injection Attacks

arXiv · Research · AI Security

Multi-Agent Framework for Threat Mitigation and Resilience in AI-Based Systems

arXiv · Research · AI Security, Models

It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents

arXiv · Research · AI Security

AegisAgent: An Autonomous Defense Agent Against Prompt Injection Attacks in LLM-HARs

arXiv · Research · AI Security

Advisories in this window

  • 39 npm advisories · 35 critical · 3 high · 1 moderate
  • 14 PyPI advisories · 2 critical · 9 high · 3 moderate
  • 13 Go advisories · 1 high · 10 moderate · 2 low
  • 4 Packagist advisories · 2 high · 2 moderate
  • 1 crates.io advisory · 1 moderate
  • 1 RubyGems 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.