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 27 June 2026 Retrospective Covers 26 June 2026 00:00 to 27 June 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-06-27/ TOP DEVELOPMENTS [1] CISA sets urgent deadline to fix Cisco flaw exploited in attacks BleepingComputer · Incident · https://bleepingcomputer.com/news/security/cisa-sets-urgent-deadline-to-fix-cisco-flaw-exploited-in-attacks [2] Polymarket customers lose $3 million in supply-chain attack BleepingComputer · Incident · https://bleepingcomputer.com/news/security/polymarket-customers-lose-3-million-in-supply-chain-attack [3] Incident Report: CVE-2026-LGTM Simon Willison · Incident · https://simonwillison.net/2026/Jun/26/incident-report [4] MCP Auto-Execution: From Git Clone to Cloud Compromise in Amazon Q VS Code Extension Wiz · Incident · https://wiz.io/blog/amazon-q-vulnerability [5] Miasma Malware Targets npm Packages and GitHub Actions in Supply Chain Attack The Hacker News · Incident · https://thehackernews.com/2026/06/miasma-malware-targets-npm-packages-and.html SCA [6] The Reciprocal Impact of Science and Software: A Cross-Corpus Analysis of How Research Shapes Software and Software Enables Research arXiv · Research · https://arxiv.org/abs/2606.28120 [7] Exploring and Exploiting Synchrony Limitations of Time-Triggered Network-Agnostic Guardians arXiv · Research · https://arxiv.org/abs/2606.27819 AGENTIC SDLC [8] For Coding Agents, the Repository Matters arXiv · Research · https://arxiv.org/abs/2606.28235 [9] How Humans, Bots, and Agents Communicate About Vulnerabilities in Pull Requests arXiv · Research · https://arxiv.org/abs/2606.28125 [10] Amazon Q Developer Flaw Could Let Malicious Repos Run Code via MCP Configs The Hacker News · Analysis · https://thehackernews.com/2026/06/amazon-q-developer-flaw-could-let.html TRUST [11] Your First GRC Agent: A Red Teamer's Walkthrough BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/your-first-grc-agent-a-red-teamers-walkthrough [12] Guardian Agents: The Next Layer of Identity Governance The Hacker News · Analysis · https://thehackernews.com/2026/06/guardian-agents-next-layer-of-identity.html MODELS [13] Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models arXiv · Research · https://arxiv.org/abs/2606.28153 [14] It Lied to a Doctor to Buy Poison Ingredients: Quantifying Real-World Misuse of Phone-use Agents arXiv · Research · https://arxiv.org/abs/2606.27944 AI SECURITY [15] RIPA: Sensory-Vector Prompt Injection Attacks on LLM-Controlled ROS 2 Robots arXiv · Research · https://arxiv.org/abs/2606.28649 [16] LLM agents security duality: a comprehensive survey of self-security and empowered cybersecurity arXiv · Research · https://arxiv.org/abs/2606.28450 ADVISORIES IN THIS WINDOW 49 npm advisories · 24 critical · 12 high · 12 moderate · 1 low 35 Go advisories · 9 critical · 9 high · 12 moderate · 5 low 13 Packagist advisories · 3 high · 7 moderate · 3 low 13 PyPI advisories · 1 critical · 6 high · 6 moderate 12 Hex advisories · 1 critical · 6 high · 4 moderate · 1 low 10 Maven advisories · 2 critical · 5 high · 3 moderate 7 RubyGems advisories · 1 critical · 3 high · 2 moderate · 1 low 4 NuGet advisories · 4 moderate 2 crates.io advisories · 1 moderate · 1 low 1 Multi-ecosystem advisory · 1 critical 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.