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 12 May 2026 · Retrospective · Covers 11 May 2026 00:00 to 12 May 2026 00:00 UTC

Read on the web

Top developments

Official CheckMarx Jenkins package compromised with infostealer

BleepingComputer · Incident · SCA

Google spotted an AI-developed zero-day before attackers could use it

CyberScoop · Research

Why Changing Passwords Doesn’t End an Active Directory Breach

BleepingComputer · Incident

SAST

Benchmarking LLM-Based Static Analysis for Secure Smart Contract Development: Reliability, Limitations, and Potential Hybrid Solutions

arXiv · Research · SAST

MARGIN: Margin-Aware Regularized Geometry for Imbalanced Vulnerability Detection

arXiv · Research · SAST

DAST

Continuous Discovery of Vulnerabilities in LLM Serving Systems with Fuzzing

arXiv · Research · DAST

From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World

arXiv · Research · DAST

Agentic SDLC

CrackMeBench: Binary Reverse Engineering for Agents

arXiv · Research · Agentic SDLC

Malicious Coding Agent Skills and the Risk of Dynamic Context

Datadog · Analysis · Agentic SDLC, AI Security

Remediation

Your Purple Team Isn't Purple — It's Just Red and Blue in the Same Room

The Hacker News · Analysis · Remediation

Trust

The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck

arXiv · Research · AI Security, Trust

Models

LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments

arXiv · Research · Models

Re-Triggering Safeguards within LLMs for Jailbreak Detection

arXiv · Research · Models

Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing

arXiv · Research · Models

AI Security

Training-Free Refusal of MCP Exploits via Retrieval-Augmented Generation

arXiv · Research · AI Security

ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?

arXiv · Research · AI Security

Content-Aware Attack Detection in LLM Agent Tool-Call Traffic: An Empirical Study of Features, Architectures, and Evaluation Protocols

arXiv · Research · AI Security

Advisories in this window

  • 41 npm advisories · 27 critical · 9 high · 5 moderate
  • 36 PyPI advisories · 2 critical · 22 high · 12 moderate
  • 20 Packagist advisories · 1 critical · 9 high · 10 moderate
  • 14 Go advisories · 1 critical · 6 high · 4 moderate · 3 low
  • 3 Hex advisories · 1 high · 1 moderate · 1 low
  • 2 Maven advisories · 1 critical · 1 high
  • 1 Multi-ecosystem advisory · 1 moderate
  • 1 crates.io 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.