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, Tuesday 7 July 2026 Retrospective Covers 6 July 2026 00:00 to 7 July 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-07-07/ TOP DEVELOPMENTS [1] Sysdig clocks first documented case of agentic ransomware CyberScoop · Incident · https://cyberscoop.com/sysdig-judepuffer-ai-agentic-ransomware-attack [2] The ‘first’ AI-run ransomware attack still needed a human TechCrunch: Security · Incident · https://techcrunch.com/2026/07/06/the-first-ai-run-ransomware-attack-still-needed-a-human [3] Opera GX Flaw Let Malicious Sites Auto-Install Mods to Steal Data From Visited Pages The Hacker News · Research · https://thehackernews.com/2026/07/opera-gx-flaw-let-malicious-sites-auto.html [4] SkillCloak Lets Malicious AI Agent Skills Evade Static Scanners with Self-Extracting Packing The Hacker News · Research · https://thehackernews.com/2026/07/new-skillcloak-technique-lets-malicious.html SAST [5] ShadowProbe: Language-Extensible Detection of Hidden Algorithmic Complexity Vulnerabilities arXiv · Research · https://arxiv.org/abs/2607.05474 [6] RustMizan: A Compilable, Contamination-Aware Benchmarking Framework for Rust Vulnerabilities arXiv · Research · https://arxiv.org/abs/2607.04729 SCA [7] Beyond Compliance: A Large Scale Study on the Completeness and Consistency of the GitHub SBOMs arXiv · Research · https://arxiv.org/abs/2607.04614 DAST [8] Use the Client Spider for Modern Web Apps ZAP (Checkmarx) · Analysis · https://zaproxy.org/blog/2026-07-06-client-spider-now-recommended TRUST [9] Governed Individuation: Cryptographically Decoupling an Agent's Learning from Its Authority arXiv · Research · https://arxiv.org/abs/2607.04613 MODELS [10] Statistical Adversaries: Natural Backdoor-like Adversarial Features in Clean Vision Datasets arXiv · Research · https://arxiv.org/abs/2607.05516 [11] Privacy-Preserving Robustness Verification for Neural Networks arXiv · Research · https://arxiv.org/abs/2607.05251 AI SECURITY [12] When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents arXiv · Research · https://arxiv.org/abs/2607.06595 [13] Untrusted Content Masking for Web Agents with Security Guarantees arXiv · Research · https://arxiv.org/abs/2607.05277 [14] Agent Data Injection Attacks are Realistic Threats to AI Agents arXiv · Research · https://arxiv.org/abs/2607.05120 ADVISORIES IN THIS WINDOW 169 npm advisories · 166 critical · 1 high · 2 moderate 35 Maven advisories · 10 critical · 15 high · 9 moderate · 1 low 23 crates.io advisories · 1 critical · 2 high · 11 moderate · 9 low 22 Go advisories · 1 critical · 9 high · 12 moderate 12 PyPI advisories · 2 critical · 6 high · 2 moderate · 2 low 6 Packagist advisories · 1 critical · 2 high · 3 moderate 1 NuGet 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.