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

Weekly, week 28 of 2026 · Retrospective · Covers 30 June 2026 11:00 to 7 July 2026 11:00 UTC

Read on the web

Top developments

CitrixBleed To Infinity And Beyond (Citrix NetScaler Pre-Auth Memory Overread CVE-2026-8451)

watchTowr · Analysis · Remediation

JadePuffer ransomware used AI agent to automate entire attack

BleepingComputer · Incident · AI Security

Adobe patches seven max severity ColdFusion, Campaign flaws

BleepingComputer · Advisory · Remediation

BeyondTrust warns of critical flaws in remote access software

BleepingComputer · Analysis · Remediation

Sysdig clocks first documented case of agentic ransomware

CyberScoop · Incident · AI Security

SAST

Multiple @immobiliarelabs Backstage Plugins Compromised on npm

StepSecurity · Incident · Agentic SDLC, SAST, SCA

The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities

arXiv · Research · Agentic SDLC, AI Security, SAST

ShadowProbe: Language-Extensible Detection of Hidden Algorithmic Complexity Vulnerabilities

arXiv · Research · SAST

RustMizan: A Compilable, Contamination-Aware Benchmarking Framework for Rust Vulnerabilities

arXiv · Research · SAST

SCA

10 Layers Deep: How StepSecurity Stops TeamPCP's Trivy Supply Chain Attack on GitHub Actions

StepSecurity · Incident · SCA

Mass npm Supply Chain Attack: 20 Leo Platform Packages Compromised

StepSecurity · Incident · SCA

Secure Registry now tells you which machine pulled a compromised package

StepSecurity · Incident · SCA

15 Malicious JetBrains Plugins Stole AI API Keys from 70,000 Developers

StepSecurity · Incident · Agentic SDLC, SCA

DAST

Using OAI Overlay to Enhance REST API Fuzzing

arXiv · Research · DAST

Execution Divergence Graphs:Effective Discovery of Control-Flows from Execution Traces as Fuzzing Feedback

arXiv · Research · DAST

Large Language Models for Fuzz Testing in Microservices: A Systematic Literature Review

arXiv · Research · DAST

From Battlefield to Boardroom: Strategic Red Teaming as an Epistemic Governance Instrument in the Age of AI

arXiv · Research · DAST, Trust

Agentic SDLC

SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review

arXiv · Research · Agentic SDLC

Can Large Language Models Generate Observability-Aware Code?

arXiv · Research · Agentic SDLC

Unicode TAG-Block Concealment of Tool-Metadata Payloads in the Model Context Protocol: An Approval-View Fidelity Gap Across Three Independent Server Implementations

arXiv · Research · Agentic SDLC

SkillCloak Lets Malicious AI Agent Skills Evade Static Scanners with Self-Extracting Packing

The Hacker News · Research · Agentic SDLC, AI Security

Remediation

Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis

arXiv · Research · Models, Remediation

Opera GX Flaw Let Malicious Sites Auto-Install Mods to Steal Data From Visited Pages

The Hacker News · Research · Remediation

Cisco finally confirms attackers exploiting Unified CM flaw

BleepingComputer · Analysis · Remediation

GPT-5.5-Cyber built a zlib fuzzing lab in a day

Trail of Bits · Analysis · Remediation

Trust

Cool New Whitepaper

SPDX · Research · SCA, Trust

Governed Individuation: Cryptographically Decoupling an Agent's Learning from Its Authority

arXiv · Research · Trust

Agentao: A Policy-Governed Runtime Harness for Embeddable Tool-Using LLM Agents

arXiv · Research · AI Security, Trust

Macro-Prudential AI Governance: A Two-Layer Early Warning and Response System for Frontier AI

arXiv · Research · Trust

Models

Auditing of Unlearning Algorithms

arXiv · Research · Models

Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor

arXiv · Research · Models

Statistical Adversaries: Natural Backdoor-like Adversarial Features in Clean Vision Datasets

arXiv · Research · Models

Privacy-Preserving Robustness Verification for Neural Networks

arXiv · Research · Models

AI Security

The ‘first’ AI-run ransomware attack still needed a human

TechCrunch: Security · Incident · AI Security

Phantom Squatting: AI-Hallucinated Domains as a Software Supply Chain Vector

Palo Alto Networks · Analysis · AI Security, SCA

Microsoft Warns Poisoned MCP Tool Descriptions Can Make AI Agents Leak Data

The Hacker News · Incident · AI Security

When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents

arXiv · Research · AI Security

Advisories in this window

  • 286 npm advisories · 215 critical · 40 high · 30 moderate · 1 low
  • 81 Go advisories · 14 critical · 33 high · 29 moderate · 5 low
  • 61 crates.io advisories · 2 critical · 9 high · 39 moderate · 11 low
  • 55 Maven advisories · 11 critical · 29 high · 11 moderate · 4 low
  • 51 PyPI advisories · 5 critical · 32 high · 5 moderate · 9 low
  • 36 Packagist advisories · 3 critical · 15 high · 14 moderate · 4 low
  • 10 NuGet advisories · 5 high · 4 moderate · 1 low
  • 5 Hex advisories · 1 critical · 4 moderate
  • 1 RubyGems advisory · 1 high

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.