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 4 of 2026 · Retrospective · Covers 13 January 2026 12:00 to 20 January 2026 12:00 UTC

Read on the web

Top developments

Cisco finally fixes AsyncOS zero-day exploited since November

BleepingComputer · Incident · Remediation

Microsoft January 2026 Patch Tuesday fixes 3 zero-days, 114 flaws

BleepingComputer · Advisory · Remediation

Reprompt attack hijacked Microsoft Copilot sessions for data theft

BleepingComputer · Research · Agentic SDLC, AI Security

A single click mounted a covert, multistage attack against Copilot

Ars Technica: Security · Incident · Agentic SDLC, Remediation

CISA’s secure-software buying tool had a simple XSS vulnerability of its own

CyberScoop · Research · Remediation

SAST

Community-powered security with AI: an open source framework for security research

GitHub · Standard / policy · AI Security, SAST

Enhancing Fuzz Testing Efficiency through Automated Fuzz Target Generation

arXiv · Research · DAST, SAST

Multi-Agent Taint Specification Extraction for Vulnerability Detection

arXiv · Research · SAST

Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale

arXiv · Research · AI Security, SAST

SCA

CodeBreach: Infiltrating the AWS Console Supply Chain and Hijacking AWS GitHub Repositories via CodeBuild

Wiz · Analysis · SCA

Five Malicious Chrome Extensions Impersonate Workday and NetSuite to Hijack Accounts

The Hacker News · Incident · SCA

Evelyn Stealer Malware Abuses VS Code Extensions to Steal Developer Credentials and Crypto

The Hacker News · Research · SCA

Efficient Code Analysis via Graph Representation Learning-Guided Large Language Models

arXiv · Research · SCA

DAST

FeatureFuzz: Treating Bug-prone Features as Core Primitives for Compiler Fuzzing

arXiv · Research · DAST

SimFuzz: Similarity-guided Block-level Mutation for RISC-V Processor Fuzzing

arXiv · Research · DAST

OWASP PTK Integration with ZAP

ZAP (Checkmarx) · Analysis · DAST, SAST

Agentic SDLC

Prompt Injection Mitigation with Agentic AI, Nested Learning, and AI Sustainability via Semantic Caching

arXiv · Research · Agentic SDLC, AI Security

Building an agentic memory system for GitHub Copilot

GitHub · Analysis · Agentic SDLC

[Webinar] Securing Agentic AI: From MCPs and Tool Access to Shadow API Key Sprawl

The Hacker News · Analysis · Agentic SDLC

Remediation

Microsoft Patch Tuesday addresses 112 defects, including one actively exploited zero-day

CyberScoop · Advisory · Remediation

Palo Alto Networks warns of DoS bug letting hackers disable firewalls

BleepingComputer · Analysis · Remediation

Many Bluetooth devices with Google Fast Pair vulnerable to “WhisperPair” hack

Ars Technica: Security · Research · Remediation

Microsoft releases OOB Windows updates to fix shutdown, Cloud PC bugs

BleepingComputer · Analysis · Remediation

Trust

Implementing data governance on AWS: Automation, tagging, and lifecycle strategy – Part 2

AWS Security Blog · Research · Trust

Frontier AI Auditing: Toward Rigorous Third-Party Assessment of Safety and Security Practices at Leading AI Companies

arXiv · Research · Trust

Agentic Pipelines in Embedded Software Engineering: Emerging Practices and Challenges

arXiv · Research · Trust

How to automate just-in-time access to applications with Tines

BleepingComputer · Guide · Trust

Models

RECAP: A Resource-Efficient Method for Adversarial Prompting in Large Language Models

arXiv · Research · Models

SilentDrift: Exploiting Action Chunking for Stealthy Backdoor Attacks on Vision-Language-Action Models

arXiv · Research · Models

Sockpuppetting: Jailbreaking LLMs by Combining Prefilling with Optimization

arXiv · Research · Models

In Vino Veritas and Vulnerabilities: Examining LLM Safety via Drunk Language Inducement

arXiv · Research · Models

AI Security

PINA: Prompt Injection Attack against Navigation Agents

arXiv · Research · AI Security

Google Gemini Prompt Injection Flaw Exposed Private Calendar Data via Malicious Invites

The Hacker News · Research · AI Security

MirrorGuard: Toward Secure Computer-Use Agents via Simulation-to-Real Reasoning Correction

arXiv · Research · AI Security

TrojanPraise: Jailbreak LLMs via Benign Fine-Tuning

arXiv · Research · AI Security, Models

Advisories in this window

  • 140 npm advisories · 109 critical · 14 high · 13 moderate · 4 low
  • 23 Packagist advisories · 6 high · 11 moderate · 6 low
  • 20 PyPI advisories · 2 critical · 11 high · 5 moderate · 2 low
  • 18 Go advisories · 1 critical · 6 high · 10 moderate · 1 low
  • 14 Maven advisories · 7 high · 5 moderate · 2 low
  • 6 crates.io advisories · 1 critical · 3 high · 1 moderate · 1 low
  • 3 RubyGems advisories · 1 critical · 1 high · 1 moderate
  • 2 NuGet advisories · 1 critical · 1 moderate
  • 1 Multi-ecosystem advisory · 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.