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, Monday 6 April 2026 · Retrospective · Covers 5 April 2026 00:00 to 6 April 2026 00:00 UTC

Read on the web

Top developments

New FortiClient EMS flaw exploited in attacks, emergency patch released

BleepingComputer · Incident · Remediation

36 Malicious npm Packages Exploited Redis, PostgreSQL to Deploy Persistent Implants

The Hacker News · Incident · SCA

Hackers exploit React2Shell in automated credential theft campaign

BleepingComputer · Incident

SCA

Causality Laundering: Denial-Feedback Leakage in Tool-Calling LLM Agents

arXiv · Research · SCA

DAST

Triggering and Detecting Exploitable Library Vulnerability from the Client by Directed Greybox Fuzzing

arXiv · Research · DAST

Agentic SDLC

Humans Integrate, Agents Fix: How Agent-Authored Pull Requests Are Referenced in Practice

arXiv · Research · Agentic SDLC

scan-for-secrets 0.1

Simon Willison · Analysis · Agentic SDLC

Trust

Governance-Constrained Agentic AI: Blockchain-Enforced Human Oversight for Safety-Critical Wildfire Monitoring

arXiv · Research · Trust

Automating Cloud Security and Forensics Through a Secure-by-Design Generative AI Framework

arXiv · Research · AI Security, Models, Trust

Models

FreakOut-LLM: The Effect of Emotional Stimuli on Safety Alignment

arXiv · Research · Models

CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks

arXiv · Research · Models

SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement

arXiv · Research · Models

AI Security

LLM-Enabled Open-Source Systems in the Wild: An Empirical Study of Vulnerabilities in GitHub Security Advisories

arXiv · Research · AI Security

TraceGuard: Structured Multi-Dimensional Monitoring as a Collusion-Resistant Control Protocol

arXiv · Research · AI Security

Advisories in this window

  • 1 PyPI advisory · 1 low

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.