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 Monthly, August 2024 Retrospective Covers August 2024 Web: https://keryn.dev/headlines/monthly/2024-08/ TOP DEVELOPMENTS [1] Google tags a tenth Chrome zero-day as exploited this year BleepingComputer · Incident · https://bleepingcomputer.com/news/security/google-tags-a-tenth-chrome-zero-day-as-exploited-this-year [2] Google fixes Android kernel zero-day exploited in targeted attacks BleepingComputer · Incident · https://bleepingcomputer.com/news/security/google-fixes-android-kernel-zero-day-exploited-in-targeted-attacks [3] Microsoft August 2024 Patch Tuesday fixes 9 zero-days, 6 exploited BleepingComputer · Advisory · https://bleepingcomputer.com/news/microsoft/microsoft-august-2024-patch-tuesday-fixes-9-zero-days-6-exploited [4] CVE-2024-38107: Microsoft Windows Power Dependency Coordinator Privilege Escalation Vulnerability added to CISA's Known Exploited Vulnerabilities catalog CISA · Advisory · https://cisa.gov/known-exploited-vulnerabilities-catalog?search_api_fulltext=CVE-2024-38107 [5] Atlassian Confluence Vulnerability Exploited in Crypto Mining Campaigns The Hacker News · Incident · https://thehackernews.com/2024/08/atlassian-confluence-vulnerability.html [6] Windows 0-day was exploited by North Korea to install advanced rootkit Ars Technica: Security · Incident · https://arstechnica.com/security/2024/08/windows-0-day-was-exploited-by-north-korea-to-install-advanced-rootkit [7] Chinese government hackers targeted US internet providers with zero-day exploit, researchers say TechCrunch: Security · Research · https://techcrunch.com/2024/08/27/chinese-government-hackers-targeted-u-s-internet-providers-with-zero-day-exploit-researchers-say [8] GitHub Enterprise Server vulnerable to critical auth bypass flaw BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/github-enterprise-server-vulnerable-to-critical-auth-bypass-flaw [9] CISA warns critical SolarWinds RCE bug is exploited in attacks BleepingComputer · Incident · https://bleepingcomputer.com/news/security/cisa-warns-critical-solarwinds-rce-bug-is-exploited-in-attacks [10] New Windows SmartScreen bypass exploited as zero-day since March BleepingComputer · Incident · https://bleepingcomputer.com/news/microsoft/new-windows-smartscreen-bypass-exploited-as-zero-day-since-march SAST [11] BaseMirror: Automatic Reverse Engineering of Baseband Commands from Android's Radio Interface Layer arXiv · Research · https://arxiv.org/abs/2409.00475 [12] Outside the Comfort Zone: Analysing LLM Capabilities in Software Vulnerability Detection arXiv · Research · https://arxiv.org/abs/2408.16400 [13] ANVIL: Anomaly-based Vulnerability Identification without Labelled Training Data arXiv · Research · https://arxiv.org/abs/2408.16028 [14] CrossInspector: A Static Analysis Approach for Cross-Contract Vulnerability Detection arXiv · Research · https://arxiv.org/abs/2408.15292 [15] ARAP: Demystifying Anti Runtime Analysis Code in Android Apps arXiv · Research · https://arxiv.org/abs/2408.11080 SCA [16] Malware force-installs Chrome extensions on 300,000 browsers, patches DLLs BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/malware-force-installs-chrome-extensions-on-300-000-browsers-patches-dlls [17] StackExchange abused to spread malicious PyPi packages as answers BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/stackexchange-abused-to-spread-malicious-pypi-packages-as-answers [18] Year-Long Campaign of Malicious npm Packages Targeting Roblox Users Checkmarx · Incident · https://checkmarx.com/blog/year-long-campaign-of-malicious-npm-packages-targeting-roblox-users [19] Chain-of-Experts (CoE): Reverse Engineering Software Bills of Materials for JavaScript Application Bundles through Code Clone Search arXiv · Research · https://arxiv.org/abs/2408.16198 [20] CoSAI at the IJIS AI Summit CoSAI · Analysis · https://coalitionforsecureai.org/cosai-at-the-ijis-ai-summit DAST [21] BreachSeek: A Multi-Agent Automated Penetration Tester arXiv · Research · https://arxiv.org/abs/2409.03789 [22] Ethical Hacking and its role in Cybersecurity arXiv · Research · https://arxiv.org/abs/2408.16033 [23] CIPHER: Cybersecurity Intelligent Penetration-testing Helper for Ethical Researcher arXiv · Research · https://arxiv.org/abs/2408.11650 [24] Vulseye: Detect Smart Contract Vulnerabilities via Stateful Directed Graybox Fuzzing arXiv · Research · https://arxiv.org/abs/2408.10116 [25] DeepREST: Automated Test Case Generation for REST APIs Exploiting Deep Reinforcement Learning arXiv · Research · https://arxiv.org/abs/2408.08594 AGENTIC SDLC [26] Microsoft Copilot: From Prompt Injection to Exfiltration of Personal Information Embrace The Red · Analysis · https://embracethered.com/blog/posts/2024/m365-copilot-prompt-injection-tool-invocation-and-data-exfil-using-ascii-smuggling [27] Top companies ground Microsoft Copilot over data governance concerns Simon Willison · Analysis · https://simonwillison.net/2024/Aug/23/microsoft-copilot-data-governance [28] Microsoft Patches Critical Copilot Studio Vulnerability Exposing Sensitive Data The Hacker News · Research · https://thehackernews.com/2024/08/microsoft-patches-critical-copilot.html [29] Security Attacks on LLM-based Code Completion Tools arXiv · Research · https://arxiv.org/abs/2408.11006 [30] How Well Do Large Language Models Serve as End-to-End Secure Code Agents for Python? arXiv · Research · https://arxiv.org/abs/2408.10495 REMEDIATION [31] North Korean threat actor Citrine Sleet exploiting Chromium zero-day Microsoft · Analysis · https://microsoft.com/en-us/security/blog/2024/08/30/north-korean-threat-actor-citrine-sleet-exploiting-chromium-zero-day [32] Critical Progress WhatsUp RCE flaw now under active exploitation BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/critical-progress-whatsup-rce-flaw-now-under-active-exploitation [33] Microsoft Issues Patches for 90 Flaws, Including 10 Critical Zero-Days The Hacker News · Advisory · https://thehackernews.com/2024/08/microsoft-issues-patches-for-90-flaws.html [34] SonicWall warns of critical access control flaw in SonicOS BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/sonicwall-warns-of-critical-access-control-flaw-in-sonicos [35] Fortra fixes critical FileCatalyst Workflow hardcoded password issue BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/fortra-fixes-critical-filecatalyst-workflow-hardcoded-password-issue TRUST [36] The potential functions of an international institution for AI safety. Insights from adjacent policy areas and recent trends arXiv · Research · https://arxiv.org/abs/2409.10536 [37] Verification methods for international AI agreements arXiv · Research · https://arxiv.org/abs/2408.16074 [38] Ethical AI Governance: Methods for Evaluating Trustworthy AI arXiv · Research · https://arxiv.org/abs/2409.07473 [39] Innovative Supply Chain Security for Enterprise Cloud Platform Service OpenSSF · Analysis · https://openssf.org/blog/2024/08/27/innovative-supply-chain-security-for-enterprise-cloud-platform-service [40] Do Responsible AI Artifacts Advance Stakeholder Goals? Four Key Barriers Perceived by Legal and Civil Stakeholders arXiv · Research · https://arxiv.org/abs/2408.12047 MODELS [41] Extracting Prompts by Inverting LLM Outputs Simon Willison · Research · https://simonwillison.net/2024/Aug/2/extracting-prompts-by-inverting-llm-outputs [42] Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks arXiv · Research · https://arxiv.org/abs/2409.00426 [43] Rethinking Backdoor Detection Evaluation for Language Models arXiv · Research · https://arxiv.org/abs/2409.00399 [44] HSF: Defending against Jailbreak Attacks with Hidden State Filtering arXiv · Research · https://arxiv.org/abs/2409.03788 [45] Emerging Vulnerabilities in Frontier Models: Multi-Turn Jailbreak Attacks arXiv · Research · https://arxiv.org/abs/2409.00137 AI SECURITY [46] Data Exfiltration from Slack AI via indirect prompt injection Simon Willison · Analysis · https://simonwillison.net/2024/Aug/20/data-exfiltration-from-slack-ai [47] Google AI Studio: LLM-Powered Data Exfiltration Hits Again! Quickly Fixed. Embrace The Red · Research · https://embracethered.com/blog/posts/2024/google-ai-studio-data-exfiltration-now-fixed [48] Atoxia: Red-teaming Large Language Models with Target Toxic Answers arXiv · Research · https://arxiv.org/abs/2408.14853 [49] The dangers of AI agents unfurling hyperlinks and what to do about it Simon Willison · Analysis · https://simonwillison.net/2024/Aug/21/dangers-of-ai-agents-unfurling [50] Hide Your Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Carrier Articles arXiv · Research · https://arxiv.org/abs/2408.11182 ADVISORIES IN THIS WINDOW 235 npm advisories · 202 critical · 10 high · 19 moderate · 4 low 74 Go advisories · 8 critical · 19 high · 45 moderate · 2 low 48 Packagist advisories · 14 high · 32 moderate · 2 low 37 PyPI advisories · 1 critical · 13 high · 19 moderate · 4 low 34 Maven advisories · 6 critical · 18 high · 9 moderate · 1 low 9 crates.io advisories · 4 high · 4 moderate · 1 low 6 NuGet advisories · 1 high · 5 moderate 6 RubyGems advisories · 1 critical · 1 high · 4 moderate 5 Multi-ecosystem advisories · 2 high · 3 moderate 2 GitHub Actions advisories · 1 high · 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.