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 Web: https://keryn.dev/headlines/daily/2026-08-01/ TOP DEVELOPMENTS [1] Online ad firm Adform’s script compromised to steal cryptocurrency BleepingComputer · Incident · https://bleepingcomputer.com/news/security/online-ad-firm-adforms-script-compromised-to-steal-cryptocurrency [2] What the Hugging Face breach reveals about defense in the age of agentic AI CyberScoop · Incident · https://cyberscoop.com/hugging-face-breach-agentic-ai-security-op-ed [3] Amgen says cloud data breach exposed patient health, proprietary info BleepingComputer · Incident · https://bleepingcomputer.com/news/security/amgen-says-cloud-data-breach-exposed-patient-health-proprietary-info SAST [4] CWEEP: A Lexical Static Analysis Framework for CWE Early Prevention arXiv · Research · https://arxiv.org/abs/2607.29604 SCA [5] Exposed by Design: A Dynamic Security Assessment of Internet-Facing MCP Servers at Scale arXiv · Research · https://arxiv.org/abs/2608.00150 [6] Anthropic's Claude breached 3 orgs, uploaded PyPI malware during tests BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/anthropics-claude-breached-3-orgs-uploaded-pypi-malware-during-tests AGENTIC SDLC [7] From Code Review to Code Critique: Intent, Drift, and Spotlight for AI-Generated Diffs at Scale arXiv · Research · https://arxiv.org/abs/2607.29516 [8] AgenticRepair: Multi-Faceted Program Context Engineering for Agentic Vulnerability Repair arXiv · Research · https://arxiv.org/abs/2607.29422 [9] Automated Testing and Repair for Verified Compilers Generated by a Coding Agent arXiv · Research · https://arxiv.org/abs/2607.28928 TRUST [10] Advancing responsible AI across Europe OpenAI News · Analysis · https://openai.com/index/advancing-responsible-ai-across-europe MODELS [11] Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Turn Attacks arXiv · Research · https://arxiv.org/abs/2608.00134 [12] Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents arXiv · Research · https://arxiv.org/abs/2607.29254 [13] Alignment Is Local: A Paired Diagnostic for GUI Agents under User-Side Persuasion arXiv · Research · https://arxiv.org/abs/2607.29199 AI SECURITY [14] Claude published malicious code to the Internet and attacked 3 real companies Ars Technica: Security · Analysis · https://arstechnica.com/security/2026/07/likely-illegally-claude-gained-access-to-3-networks-will-anthropic-be-held-to-account [15] From Monoliths to Swarms: A Study of Attack Surface Evolution in the Transition to Multi-Agent Web Systems arXiv · Research · https://arxiv.org/abs/2608.00202 [16] Anthropic’s Opus 5 Is Better at Resisting Prompt Injection Schneier on Security · Analysis · https://schneier.com/blog/archives/2026/07/anthropics-opus-5-is-better-at-resisting-prompt-injection.html 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: https://keryn.dev/headlines/advisories/ Titles, links and short excerpts only; every item links to its source. Preview: the unsubscribe link and Keryn's postal address are added to each email when it is sent.