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 9 May 2026 Retrospective Covers 8 May 2026 00:00 to 9 May 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-05-09/ TOP DEVELOPMENTS [1] Flaw in Claude’s Chrome extension allowed ‘any’ other plugin to hijack victims’ AI CyberScoop · Incident · https://cyberscoop.com/claude-chrome-extension-allows-plugins-to-hijack-ai [2] Detecting Web Server Probing & Fuzzing in Traefik with Automated Cloudflare Response Elastic · Research · https://elastic.co/security-labs/blog/detecting-web-server-probing-and-fuzzing [3] Quasar Linux RAT Steals Developer Credentials for Software Supply Chain Compromise The Hacker News · Incident · https://thehackernews.com/2026/05/quasar-linux-rat-steals-developer.html SAST [4] Longitudinal Analyses of SAST Tools: A CodeQL Case Study arXiv · Research · https://arxiv.org/abs/2605.07900 [5] Unsafe by Flow: Uncovering Bidirectional Data-Flow Risks in MCP Ecosystem arXiv · Research · https://arxiv.org/abs/2605.07836 [6] Securing the Dark Matter: A Semantic-Enhanced Neuro-Symbolic Framework for Supply Chain Analysis of Opaque Industrial Software arXiv · Research · https://arxiv.org/abs/2605.07737 SCA [7] Kettle: Attested builds for verifiable software provenance arXiv · Research · https://arxiv.org/abs/2605.08363 [8] Seed Hijacking of LLM Sampling and Quantum Random Number Defense arXiv · Research · https://arxiv.org/abs/2605.08313 [9] Cross-Modal Backdoors in Multimodal Large Language Models arXiv · Research · https://arxiv.org/abs/2605.07490 AGENTIC SDLC [10] Using Claude Code: The Unreasonable Effectiveness of HTML Simon Willison · Analysis · https://simonwillison.net/2026/May/8/unreasonable-effectiveness-of-html [11] SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code via Prompt Optimization arXiv · Research · https://arxiv.org/abs/2605.08382 [12] Collaborator or Assistant? How AI Coding Agents Partition Work Across Pull Request Lifecycles arXiv · Research · https://arxiv.org/abs/2605.08017 REMEDIATION [13] Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub Actions arXiv · Research · https://arxiv.org/abs/2605.07135 MODELS [14] When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks arXiv · Research · https://arxiv.org/abs/2605.08460 [15] The Attacker in the Mirror: Breaking Self-Consistency in Safety via Anchored Bipolicy Self-Play arXiv · Research · https://arxiv.org/abs/2605.08427 [16] GLiGuard: Schema-Conditioned Classification for LLM Safeguard arXiv · Research · https://arxiv.org/abs/2605.07982 AI SECURITY [17] LLM Advertisement based on Neuron Auctions arXiv · Research · https://arxiv.org/abs/2605.08326 [18] WebTrap: Stealthy Mid-Task Hijacking of Browser Agents During Navigation arXiv · Research · https://arxiv.org/abs/2605.08310 ADVISORIES IN THIS WINDOW 36 PyPI advisories · 2 critical · 12 high · 21 moderate · 1 low 28 Go advisories · 6 critical · 8 high · 12 moderate · 2 low 21 npm advisories · 5 critical · 10 high · 6 moderate 8 Packagist advisories · 2 critical · 2 high · 4 moderate 7 Maven advisories · 4 high · 3 moderate 3 RubyGems advisories · 3 moderate 3 Hex advisories · 2 high · 1 low 2 NuGet advisories · 2 moderate 2 crates.io advisories · 1 critical · 1 high 1 Multi-ecosystem advisory · 1 high 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.