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, Friday 13 February 2026 Retrospective Covers 12 February 2026 00:00 to 13 February 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-02-13/ TOP DEVELOPMENTS [1] Critical BeyondTrust RCE flaw now exploited in attacks, patch now BleepingComputer · Incident · https://bleepingcomputer.com/news/security/critical-beyondtrust-rce-flaw-now-exploited-in-attacks-patch-now [2] Google says hackers are abusing Gemini AI for all attacks stages BleepingComputer · Research · https://bleepingcomputer.com/news/security/google-says-hackers-are-abusing-gemini-ai-for-all-attacks-stages [3] Lazarus Campaign Plants Malicious Packages in npm and PyPI Ecosystems The Hacker News · Incident · https://thehackernews.com/2026/02/lazarus-campaign-plants-malicious.html SCA [4] Community Concealment from Graph Neural Networks arXiv · Research · https://arxiv.org/abs/2602.12250 [5] AMOS infostealer targets macOS through a popular AI app BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/amos-infostealer-targets-macos-through-a-popular-ai-app [6] Last Week in AppSec for 12. Feb 2026 Checkmarx · Analysis · https://checkmarx.com/zero-post/last-week-in-appsec-for-11-feb-2026 AGENTIC SDLC [7] Introducing GPT-5.3-Codex-Spark OpenAI News · Release · https://openai.com/index/introducing-gpt-5-3-codex-spark REMEDIATION [8] Apple fixes zero-day flaw used in 'extremely sophisticated' attacks BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/apple-fixes-zero-day-flaw-used-in-extremely-sophisticated-attacks MODELS [9] Sparse Autoencoders are Capable LLM Jailbreak Mitigators arXiv · Research · https://arxiv.org/abs/2602.12418 [10] Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models arXiv · Research · https://arxiv.org/abs/2602.11495 [11] Future Mining: Learning for Safety and Security arXiv · Research · https://arxiv.org/abs/2602.11472 AI SECURITY [12] Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward arXiv · Research · https://arxiv.org/abs/2602.12430 [13] MalTool: Malicious Tool Attacks on LLM Agents arXiv · Research · https://arxiv.org/abs/2602.12194 ADVISORIES IN THIS WINDOW 11 Go advisories · 5 high · 5 moderate · 1 low 7 npm advisories · 1 critical · 2 high · 3 moderate · 1 low 5 crates.io advisories · 3 critical · 1 moderate · 1 low 1 Packagist advisory · 1 high 1 Maven 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.