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 13 June 2026 · Retrospective · Covers 12 June 2026 00:00 to 13 June 2026 00:00 UTC

Read on the web

Top developments

Agentjacking Attack Tricks AI Coding Agents Into Running Malicious Code

The Hacker News · Research · Agentic SDLC, AI Security

LangGraph Flaw Chain Exposes Self-Hosted AI Agents to Remote Code Execution

The Hacker News · Research · Remediation

Over 400 Arch Linux packages compromised to push rootkit, infostealer

BleepingComputer · Incident

SAST

Security in a Workflow: Exploring Role-Based Agentic Architectures for Vulnerability Handling

arXiv · Research · SAST

Evaluating LLMs for Obfuscation Detection and Classification in Android Apps

arXiv · Research · SAST

SCA

Early Warning Signs of Supply-Chain Attacks Live in the Dark Web

BleepingComputer · Analysis · SCA

Defending the Core: A Centrality-Based Protection Strategy for Supply Chain Security in npm Dependency Network

arXiv · Research · SCA

DAST

Investigating Metamorphic Fuzz Oracle Enhancement via Large Language Models

arXiv · Research · DAST

Agentic SDLC

tap: A File-Based Protocol for Heterogeneous LLM Agent Collaboration

arXiv · Research · Agentic SDLC

AI code review tools: Key benefits and 8 tools to know in 2026

Mend.io · Analysis · Agentic SDLC

Remediation

PeopleSoft 0-day affecting hundreds of organizations steals gigabytes of data

Ars Technica: Security · Analysis · Remediation

Trust

Regulating the Machine Contributor: Governance and Policy Alignment in Open Source

arXiv · Research · Trust

Final Authority in AI Governance: Frontier-Provider Sovereignty and Action-Centered Deployer Governance

arXiv · Research · Trust

Models

From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails

arXiv · Research · AI Security, Models

A Low-Rank Subspace Analysis of LLM Interventions

arXiv · Research · Models

BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems

arXiv · Research · Models

AI Security

Security Engineering of OpenClaw: Analyzing Attack Surface Expansion and Trust-Boundary Violations

arXiv · Research · AI Security

Isolating LLM Alignment from Regex: Zero Coverage and Metric-Dependent Divergence Under Adversarial Mutation

arXiv · Research · AI Security

Advisories in this window

  • 25 npm advisories · 16 critical · 3 high · 5 moderate · 1 low
  • 21 Go advisories · 10 high · 10 moderate · 1 low
  • 17 Maven advisories · 5 critical · 6 high · 6 moderate
  • 16 Packagist advisories · 5 high · 9 moderate · 2 low
  • 6 PyPI advisories · 1 critical · 2 high · 2 moderate · 1 low
  • 5 Swift advisories · 2 high · 3 moderate
  • 2 crates.io advisories · 1 high · 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.