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, Thursday 19 February 2026 Retrospective Covers 18 February 2026 00:00 to 19 February 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-02-19/ TOP DEVELOPMENTS [1] CVE-2021-22175: GitLab Server-Side Request Forgery (SSRF) Vulnerability added to CISA's Known Exploited Vulnerabilities catalog CISA · Advisory · https://cisa.gov/known-exploited-vulnerabilities-catalog?search_api_fulltext=CVE-2021-22175 [2] Would You Click ‘Accept’? Automatically detecting malicious Azure OAuth applications using LLMs Wiz · Research · https://wiz.io/blog/detecting-malicious-oauth-applications [3] Exact Certification of Data-Poisoning Attacks Using Mixed-Integer Programming arXiv · Research · https://arxiv.org/abs/2602.16944 SCA [4] An Evaluation of Large Language Models for Detection of Malicious Python Packages arXiv · Research · https://arxiv.org/abs/2602.16304 AGENTIC SDLC [5] Can Adversarial Code Comments Fool AI Security Reviewers -- Large-Scale Empirical Study of Comment-Based Attacks and Defenses Against LLM Code Analysis arXiv · Research · https://arxiv.org/abs/2602.16741 REMEDIATION [6] AI Found Twelve New Vulnerabilities in OpenSSL Schneier on Security · Analysis · https://schneier.com/blog/archives/2026/02/ai-found-twelve-new-vulnerabilities-in-openssl.html MODELS [7] Mind the GAP: Text Safety Does Not Transfer to Tool-Call Safety in LLM Agents arXiv · Research · https://arxiv.org/abs/2602.16943 [8] DeepContext: Stateful Real-Time Detection of Multi-Turn Adversarial Intent Drift in LLMs arXiv · Research · https://arxiv.org/abs/2602.16935 [9] NeST: Neuron Selective Tuning for LLM Safety arXiv · Research · https://arxiv.org/abs/2602.16835 AI SECURITY [10] AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks arXiv · Research · https://arxiv.org/abs/2602.16901 [11] Formal Policy Enforcement for Agentic Systems arXiv · Research · https://arxiv.org/abs/2602.16708 [12] The Vulnerability of LLM Rankers to Prompt Injection Attacks arXiv · Research · https://arxiv.org/abs/2602.16752 ADVISORIES IN THIS WINDOW 42 npm advisories · 1 critical · 26 high · 15 moderate 10 PyPI advisories · 1 critical · 5 high · 3 moderate · 1 low 7 Go advisories · 2 high · 2 moderate · 3 low 7 Packagist advisories · 2 high · 5 moderate 3 Maven advisories · 1 high · 1 moderate · 1 low 1 GitHub Actions 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.