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 27 August 2025 Retrospective Covers 26 August 2025 00:00 to 27 August 2025 00:00 UTC Web: https://keryn.dev/headlines/daily/2025-08-27/ TOP DEVELOPMENTS [1] CVE-2025-7775: Citrix NetScaler Memory Overflow Vulnerability added to CISA's Known Exploited Vulnerabilities catalog CISA · Advisory · https://cisa.gov/known-exploited-vulnerabilities-catalog?search_api_fulltext=CVE-2025-7775 [2] Researchers flag code that uses AI systems to carry out ransomware attacks CyberScoop · Incident · https://cyberscoop.com/prompt-lock-eset-ransomware-research-ai-powered-prompt-injection [3] Hundreds of Salesforce customers impacted by attack spree linked to third-party AI agent CyberScoop · Research · https://cyberscoop.com/salesforce-salesloft-drift-attack-spree-google SAST [4] SIExVulTS: Sensitive Information Exposure Vulnerability Detection System using Transformer Models and Static Analysis arXiv · Research · https://arxiv.org/abs/2508.19472 [5] VISION: Robust and Interpretable Code Vulnerability Detection Leveraging Counterfactual Augmentation arXiv · Research · https://arxiv.org/abs/2508.18933 SCA [6] Releases now support immutability in public preview GitHub · Analysis · https://github.blog/changelog/2025-08-26-releases-now-support-immutability-in-public-preview AGENTIC SDLC [7] AWS Kiro: Arbitrary Code Execution via Indirect Prompt Injection Embrace The Red · Analysis · https://embracethered.com/blog/posts/2025/aws-kiro-aribtrary-command-execution-with-indirect-prompt-injection [8] GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging arXiv · Research · https://arxiv.org/abs/2508.18993 TRUST [9] A NIS2 pan-European registry for identifying and classifying essential and important entities arXiv · Research · https://arxiv.org/abs/2508.19395 [10] Securing and governing the rise of autonomous agents Microsoft · Analysis · https://microsoft.com/en-us/security/blog/2025/08/26/securing-and-governing-the-rise-of-autonomous-agents [11] Tackling Federated Unlearning as a Parameter Estimation Problem arXiv · Research · https://arxiv.org/abs/2508.19065 MODELS [12] On Surjectivity of Neural Networks: Can you elicit any behavior from your model? arXiv · Research · https://arxiv.org/abs/2508.19445 [13] An Investigation on Group Query Hallucination Attacks arXiv · Research · https://arxiv.org/abs/2508.19321 AI SECURITY [14] Piloting Claude for Chrome Simon Willison · Analysis · https://simonwillison.net/2025/Aug/26/piloting-claude-for-chrome [15] Reliable Weak-to-Strong Monitoring of LLM Agents arXiv · Research · https://arxiv.org/abs/2508.19461 ADVISORIES IN THIS WINDOW 23 PyPI advisories · 10 high · 13 moderate 4 npm advisories · 2 high · 2 moderate 3 NuGet advisories · 2 high · 1 low 2 Packagist advisories · 1 high · 1 moderate 1 Go 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.