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 5 August 2025 Retrospective Covers 4 August 2025 00:00 to 5 August 2025 00:00 UTC Web: https://keryn.dev/headlines/daily/2025-08-05/ TOP DEVELOPMENTS [1] Cursor IDE: Arbitrary Data Exfiltration Via Mermaid (CVE-2025-54132) Embrace The Red · Research · https://embracethered.com/blog/posts/2025/cursor-data-exfiltration-with-mermaid [2] Breaking NVIDIA Triton: CVE-2025-23319 - A Vulnerability Chain Leading to AI Server Takeover Wiz · Research · https://wiz.io/blog/nvidia-triton-cve-2025-23319-vuln-chain-to-ai-server [3] Ransomware gangs join attacks targeting Microsoft SharePoint servers BleepingComputer · Incident · https://bleepingcomputer.com/news/security/ransomware-gangs-join-attacks-targeting-microsoft-sharepoint-servers SAST [4] Automated Code Repair for C/C++ Static Analysis Alerts arXiv · Research · https://arxiv.org/abs/2508.02820 DAST [5] PentestJudge: Judging Agent Behavior Against Operational Requirements arXiv · Research · https://arxiv.org/abs/2508.02921 REMEDIATION [6] Google addresses six vulnerabilities in August’s Android security update CyberScoop · Analysis · https://cyberscoop.com/android-security-update-august-2025 TRUST [7] From Commits to Confidence: Towards Stability-Informed Risk Assessment in Open Source Software arXiv · Research · https://arxiv.org/abs/2508.02487 [8] DIRF: A Framework for Digital Identity Protection and Clone Governance in Agentic AI Systems arXiv · Research · https://arxiv.org/abs/2508.01997 MODELS [9] Highlight & Summarize: RAG without the jailbreaks arXiv · Research · https://arxiv.org/abs/2508.02872 [10] Large Reasoning Models Are Autonomous Jailbreak Agents arXiv · Research · https://arxiv.org/abs/2508.04039 [11] Data Security in Large Language Models: Risks, Defense, and Directions arXiv · Research · https://arxiv.org/abs/2508.02312 AI SECURITY [12] Defend LLMs Through Self-Consciousness arXiv · Research · https://arxiv.org/abs/2508.02961 [13] Quoting @himbodhisattva Simon Willison · Analysis · https://simonwillison.net/2025/Aug/4/himbodhisattva [14] Whispering Agents: An Event-driven Covert Communication Protocol For the Internet of Agents arXiv · Research · https://arxiv.org/abs/2508.02188 ADVISORIES IN THIS WINDOW 6 npm advisories · 2 critical · 3 high · 1 moderate 2 Go advisories · 1 high · 1 moderate 2 PyPI advisories · 1 critical · 1 high 1 crates.io advisory · 1 moderate 1 Packagist 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.