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

Read on the web

Top developments

Google’s August Patch Fixes Two Qualcomm Vulnerabilities Exploited in the Wild

The Hacker News · Incident · Remediation

Cursor AI Code Editor Vulnerability Enables RCE via Malicious MCP File Swaps Post Approval

The Hacker News · Research · AI Security

CVE-2020-25078: D-Link DCS-2530L and DCS-2670L Devices Unspecified Vulnerability added to CISA's Known Exploited Vulnerabilities catalog

CISA · Advisory

SCA

RX-INT: A Kernel Engine for Real-Time Detection and Analysis of In-Memory Threats

arXiv · Research · SCA

Evaluating Software Supply Chain Security in Research Software

arXiv · Research · SCA

DAST

ReFuzzer: Feedback-Driven Approach to Enhance Validity of LLM-Generated Test Programs

arXiv · Research · DAST

Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark

arXiv · Research · DAST

Agentic SDLC

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants

arXiv · Research · Agentic SDLC

Amp Code: Arbitrary Command Execution via Prompt Injection Fixed

Embrace The Red · Analysis · Agentic SDLC, AI Security

Remediation

Android gets patches for Qualcomm flaws exploited in attacks

BleepingComputer · Advisory · Remediation

On the Evaluation of Large Language Models in Multilingual Vulnerability Repair

arXiv · Research · Remediation

Trust

Trustworthiness of Legal Considerations for the Use of LLMs in Education

arXiv · Research · Trust

Evolution of AI Agent Registry Solutions: Centralized, Enterprise, and Distributed Approaches

arXiv · Research · AI Security, Trust

Models

Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning

arXiv · Research · Models

When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs

arXiv · Research · Models

BDFirewall: Towards Effective and Expeditiously Black-Box Backdoor Defense in MLaaS

arXiv · Research · Models

AI Security

AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption

arXiv · Research · AI Security

Using the NANDA Index Architecture in Practice: An Enterprise Perspective

arXiv · Research · AI Security

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

Titles, links and short excerpts only; every item links to its source. Selection is automatic; the editor's note is AI-drafted and checked as described. Preview: the unsubscribe link and Keryn's postal address are added to each email when it is sent.