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, Saturday 31 January 2026 · Retrospective · Covers 30 January 2026 00:00 to 31 January 2026 00:00 UTC

Read on the web

Top developments

Case study: Securing AI application supply chains

Microsoft · Research · AI-BOM

Safer by Diffusion, Broken by Context: Diffusion LLM's Safety Blessing and Its Failure Mode

arXiv · Research · Models

"Someone Hid It": Query-Agnostic Black-Box Attacks on LLM-Based Retrieval

arXiv · Research · Models

SAST

RVDebloater: Mode-based Adaptive Firmware Debloating for Robotic Vehicles

arXiv · Research · SAST

SolAgent: A Specialized Multi-Agent Framework for Solidity Code Generation

arXiv · Research · SAST

Sifting the Noise: A Comparative Study of LLM Agents in Vulnerability False Positive Filtering

arXiv · Research · Agentic SDLC, SAST

SCA

MITRE ATLAS (releases) v5.3.0

MITRE · Release · AI Security, SCA

Uncovering Hidden Inclusions of Vulnerable Dependencies in Real-World Java Projects

arXiv · Research · SCA

Protect your AI workloads from supply chain attacks

Chainguard · Analysis · SCA

DAST

Rust and Go directed fuzzing with LibAFL-DiFuzz

arXiv · Research · DAST, SAST

Agentic SDLC

Practical Security Guidance for Sandboxing Agentic Workflows and Managing Execution Risk

NVIDIA · Standard / policy · Agentic SDLC

Remediation

From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair

arXiv · Research · Remediation

Do Fine-Tuned LLMs Understand Vulnerabilities? An Investigation into the Semantic Trap

arXiv · Research · Remediation, SAST

SmarterMail Fixes Critical Unauthenticated RCE Flaw with CVSS 9.3 Score

The Hacker News · Analysis · Remediation

Trust

A Structured Approach to Safety Case Construction for AI Systems

arXiv · Research · Trust

Models

MITRE ATLAS (releases) v5.2.0

MITRE · Release · Models

Now You Hear Me: Audio Narrative Attacks Against Large Audio-Language Models

arXiv · Research · Models

Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures

arXiv · Research · Models

AI Security

Verifiable Manifest Signing and Transparency Enforcement for Secure MCP-Based LLM Pipelines

arXiv · Research · AI Security

Whispers of Wealth: Red-Teaming Google's Agent Payments Protocol via Prompt Injection

arXiv · Research · AI Security, Models

Advisories in this window

  • 5 PyPI advisories · 1 critical · 3 high · 1 low
  • 3 npm advisories · 1 critical · 1 high · 1 low
  • 1 Packagist advisory · 1 moderate
  • 1 Maven advisory · 1 high
  • 1 NuGet 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.