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, Wednesday 25 March 2026 · Retrospective · Covers 24 March 2026 00:00 to 25 March 2026 00:00 UTC

Read on the web

Top developments

LiteLLM and Telnyx compromised on PyPI: Tracing the TeamPCP supply chain campaign

Datadog · Incident · SCA

Popular LiteLLM PyPI package backdoored to steal credentials, auth tokens

BleepingComputer · Incident · SCA

Ghost Campaign Uses 7 npm Packages to Steal Crypto Wallets and Credentials

The Hacker News · Incident · SCA

TeamPCP Hacks Checkmarx GitHub Actions Using Stolen CI Credentials

The Hacker News · Incident · SCA

Citrix Urges Patching Critical NetScaler Flaw Allowing Unauthenticated Data Leaks

The Hacker News · Incident · Remediation

SAST

TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration

arXiv · Research · SAST

Agent Audit: A Security Analysis System for LLM Agent Applications

arXiv · Research · AI Security, SAST

Does Teaming-Up LLMs Improve Secure Code Generation? A Comprehensive Evaluation with Multi-LLMSecCodeEval

arXiv · Research · Remediation, SAST

SCA

You were one pip install away from the litellm breach. Chainguard customers weren’t.

Chainguard · Incident · AI Security, SCA

Package Managers Need to Cool Down

Simon Willison · Analysis · SCA

DAST

Towards Leveraging LLMs to Generate Abstract Penetration Test Cases from Software Architecture

arXiv · Research · DAST

Checkmarx DAST for the AI Coding Era: Runtime Security at Machine Speed

Checkmarx · Analysis · DAST

Agentic SDLC

Auto mode for Claude Code

Simon Willison · Analysis · Agentic SDLC

Code Review Agent Benchmark

arXiv · Research · Agentic SDLC

Supercharge Your SOC

Elastic · Analysis · Agentic SDLC

Remediation

Building AI-powered GitHub issue triage with the Copilot SDK

GitHub · Analysis · Remediation

Trust

Governing AI agent behavior: Aligning user, developer, role, and organizational intent

Microsoft · Analysis · Trust

Privacy-Preserving EHR Data Transformation via Geometric Operators: A Human-AI Co-Design Technical Report

arXiv · Research · Trust

From the AI Act to a European AI Agency: Completing the Union's Regulatory Architecture

arXiv · Research · Trust

Models

Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs

arXiv · Research · Models

SafeSeek: Universal Attribution of Safety Circuits in Language Models

arXiv · Research · Models

RTS-ABAC: Real-Time Server-Aided Attribute-Based Authorization & Access Control for Substation Automation Systems

arXiv · Research · Models

AI Security

The Cognitive Firewall:Securing Browser Based AI Agents Against Indirect Prompt Injection Via Hybrid Edge Cloud Defense

arXiv · Research · AI Security

Mind Your HEARTBEAT! Claw Background Execution Inherently Enables Silent Memory Pollution

arXiv · Research · AI Security

AgentRAE: Remote Action Execution through Notification-based Visual Backdoors against Screenshots-based Mobile GUI Agents

arXiv · Research · AI Security

Advisories in this window

  • 26 npm advisories · 19 critical · 4 high · 2 moderate · 1 low
  • 21 Go advisories · 5 high · 15 moderate · 1 low
  • 9 Packagist advisories · 2 high · 5 moderate · 2 low
  • 8 NuGet advisories · 1 critical · 5 high · 2 moderate
  • 4 PyPI advisories · 3 high · 1 moderate
  • 4 Maven advisories · 1 high · 2 moderate · 1 low
  • 1 RubyGems advisory · 1 moderate
  • 1 Multi-ecosystem advisory · 1 critical

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.