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, Wednesday 6 August 2025 Retrospective Covers 5 August 2025 00:00 to 6 August 2025 00:00 UTC Web: https://keryn.dev/headlines/daily/2025-08-06/ TOP DEVELOPMENTS [1] Google’s August Patch Fixes Two Qualcomm Vulnerabilities Exploited in the Wild The Hacker News · Incident · https://thehackernews.com/2025/08/google-fixes-3-android-vulnerabilities.html [2] Cursor AI Code Editor Vulnerability Enables RCE via Malicious MCP File Swaps Post Approval The Hacker News · Research · https://thehackernews.com/2025/08/cursor-ai-code-editor-vulnerability.html [3] CVE-2020-25078: D-Link DCS-2530L and DCS-2670L Devices Unspecified Vulnerability added to CISA's Known Exploited Vulnerabilities catalog CISA · Advisory · https://cisa.gov/known-exploited-vulnerabilities-catalog?search_api_fulltext=CVE-2020-25078 SCA [4] RX-INT: A Kernel Engine for Real-Time Detection and Analysis of In-Memory Threats arXiv · Research · https://arxiv.org/abs/2508.03879 [5] Evaluating Software Supply Chain Security in Research Software arXiv · Research · https://arxiv.org/abs/2508.03856 DAST [6] ReFuzzer: Feedback-Driven Approach to Enhance Validity of LLM-Generated Test Programs arXiv · Research · https://arxiv.org/abs/2508.03603 [7] Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark arXiv · Research · https://arxiv.org/abs/2508.05674 AGENTIC SDLC [8] ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants arXiv · Research · https://arxiv.org/abs/2508.03936 [9] Amp Code: Arbitrary Command Execution via Prompt Injection Fixed Embrace The Red · Analysis · https://embracethered.com/blog/posts/2025/amp-agents-that-modify-system-configuration-and-escape REMEDIATION [10] Android gets patches for Qualcomm flaws exploited in attacks BleepingComputer · Advisory · https://bleepingcomputer.com/news/security/android-gets-patches-for-qualcomm-flaws-exploited-in-attacks [11] On the Evaluation of Large Language Models in Multilingual Vulnerability Repair arXiv · Research · https://arxiv.org/abs/2508.03470 TRUST [12] Trustworthiness of Legal Considerations for the Use of LLMs in Education arXiv · Research · https://arxiv.org/abs/2508.03771 [13] Evolution of AI Agent Registry Solutions: Centralized, Enterprise, and Distributed Approaches arXiv · Research · https://arxiv.org/abs/2508.03095 MODELS [14] Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning arXiv · Research · https://arxiv.org/abs/2508.05681 [15] When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs arXiv · Research · https://arxiv.org/abs/2508.03365 [16] BDFirewall: Towards Effective and Expeditiously Black-Box Backdoor Defense in MLaaS arXiv · Research · https://arxiv.org/abs/2508.03307 AI SECURITY [17] AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption arXiv · Research · https://arxiv.org/abs/2508.03793 [18] Using the NANDA Index Architecture in Practice: An Enterprise Perspective arXiv · Research · https://arxiv.org/abs/2508.03101 ADVISORIES IN THIS WINDOW 4 Maven advisories · 2 high · 2 moderate 2 Packagist advisories · 1 critical · 1 moderate 1 crates.io advisory · 1 low 1 Go advisory · 1 high 1 npm 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.