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 1 July 2026 · Retrospective · Covers 30 June 2026 00:00 to 1 July 2026 00:00 UTC

Read on the web

Top developments

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

watchTowr · Analysis · Remediation

Cool New Whitepaper

SPDX · Research · SCA, Trust

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

The Hacker News · Incident · AI Security

Silent Swap Crypto Clipper Uses Fake Google Notes Extension to Replace Wallet Addresses

The Hacker News · Research · SCA

GuardFall Exposes Open-Source AI Coding Agents to Decades-Old Shell Injection Risks

The Hacker News · Research · Agentic SDLC

SAST

The Illusion of Safety: Multi-Tier Verification of AI vs. Human C++ Code

arXiv · Research · SAST

Open source license compliance is in public preview

GitHub · Analysis · SAST, SCA

SCA

Malicious PyPI packages give hackers control of Telegram bot servers

BleepingComputer · Analysis · SCA

Mutating the "Immutable": A Large-Scale Study of Git Tag Alterations

arXiv · Research · SCA

The State of Trusted Open Source: June 2026

Chainguard · Analysis · SCA

Agentic SDLC

MITRE ATLAS (releases) v2026.06

MITRE · Release · Agentic SDLC, AI Security, Models

New BioShocking Attack Tricks AI Browsers Into Leaking User Credentials

The Hacker News · Analysis · Agentic SDLC

Trust

When Not to Write Memory: Governing False Promotion from Correlated Agent Traces

arXiv · Research · Trust

Models

CSO-LLM: Class Subspace Orthogonalization for Post-Training Backdoor Detection and Trigger Inversion in LLMs

arXiv · Research · Models

Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming

arXiv · Research · AI Security, Models

Secure-CHG: A Comprehensive Framework for Robust and Fair Federated Learning via Hybrid Defense and Contribution-Aware Trust

arXiv · Research · Models

AI Security

New BioShocking attack manipulates AI browser into data theft

BleepingComputer · Analysis · AI Security

Securing AI agents: When AI tools move from reading to acting

Microsoft · Analysis · AI Security

Advisories in this window

  • 39 npm advisories · 38 critical · 1 high
  • 16 Go advisories · 4 critical · 8 high · 4 moderate
  • 10 Maven advisories · 7 high · 2 moderate · 1 low
  • 8 PyPI advisories · 1 critical · 2 high · 5 low
  • 6 Packagist advisories · 1 high · 4 moderate · 1 low
  • 4 Hex advisories · 4 moderate
  • 2 NuGet 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.