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 1 August 2026 · Retrospective · Covers 31 July 2026 00:00 to 1 August 2026 00:00 UTC

Read on the web

Top developments

Online ad firm Adform’s script compromised to steal cryptocurrency

BleepingComputer · Incident · SCA

What the Hugging Face breach reveals about defense in the age of agentic AI

CyberScoop · Incident · AI Security

Amgen says cloud data breach exposed patient health, proprietary info

BleepingComputer · Incident

SAST

CWEEP: A Lexical Static Analysis Framework for CWE Early Prevention

arXiv · Research · SAST

SCA

Exposed by Design: A Dynamic Security Assessment of Internet-Facing MCP Servers at Scale

arXiv · Research · AI Security, SCA

Anthropic's Claude breached 3 orgs, uploaded PyPI malware during tests

BleepingComputer · Analysis · SCA

Agentic SDLC

From Code Review to Code Critique: Intent, Drift, and Spotlight for AI-Generated Diffs at Scale

arXiv · Research · Agentic SDLC

AgenticRepair: Multi-Faceted Program Context Engineering for Agentic Vulnerability Repair

arXiv · Research · Agentic SDLC, Remediation

Automated Testing and Repair for Verified Compilers Generated by a Coding Agent

arXiv · Research · Agentic SDLC, Models

Trust

Advancing responsible AI across Europe

OpenAI News · Analysis · Trust

Models

Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Turn Attacks

arXiv · Research · Models

Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents

arXiv · Research · Models

Alignment Is Local: A Paired Diagnostic for GUI Agents under User-Side Persuasion

arXiv · Research · AI Security, Models

AI Security

Claude published malicious code to the Internet and attacked 3 real companies

Ars Technica: Security · Analysis · AI Security

From Monoliths to Swarms: A Study of Attack Surface Evolution in the Transition to Multi-Agent Web Systems

arXiv · Research · AI Security

Anthropic’s Opus 5 Is Better at Resisting Prompt Injection

Schneier on Security · Analysis · AI Security

Advisories in this window

  • 102 npm advisories · 86 critical · 6 high · 9 moderate · 1 low
  • 26 PyPI advisories · 13 critical · 10 high · 3 moderate
  • 10 Go advisories · 2 critical · 2 high · 5 moderate · 1 low
  • 4 Packagist advisories · 2 high · 2 moderate
  • 4 Maven advisories · 2 high · 2 moderate
  • 2 RubyGems advisories · 1 high · 1 moderate
  • 1 crates.io advisory · 1 moderate
  • 1 NuGet advisory · 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.