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 Weekly, week 33 of 2025 Retrospective Covers 5 August 2025 11:00 to 12 August 2025 11:00 UTC Web: https://keryn.dev/headlines/weekly/2025-W33/ 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] OpenHands and the Lethal Trifecta: How Prompt Injection Can Leak Access Tokens Embrace The Red · Incident · https://embracethered.com/blog/posts/2025/openhands-the-lethal-trifecta-strikes-again [3] How Devin AI Can Leak Your Secrets via Multiple Means Embrace The Red · Incident · https://embracethered.com/blog/posts/2025/devin-can-leak-your-secrets [4] AI Kill Chain in Action: Devin AI Exposes Ports to the Internet with Prompt Injection Embrace The Red · Research · https://embracethered.com/blog/posts/2025/devin-ai-kill-chain-exposing-ports [5] CISA orders fed agencies to patch new Exchange flaw by Monday BleepingComputer · Advisory · https://bleepingcomputer.com/news/security/cisa-orders-fed-agencies-to-patch-new-cve-2025-53786-exchange-flaw SAST [6] WhyFlow: Interrogative Debugger for Sensemaking Taint Analysis arXiv · Research · https://arxiv.org/abs/2508.07198 [7] ScamDetect: Towards a Robust, Agnostic Framework to Uncover Threats in Smart Contracts arXiv · Research · https://arxiv.org/abs/2508.07094 [8] OpenSSF at DEF CON 33: AI Cyber Challenge (AIxCC), MLSecOps, and Securing Critical Infrastructure OpenSSF · Analysis · https://openssf.org/blog/2025/08/06/openssf-at-def-con-33-ai-cyber-challenge-aixcc-mlsecops-and-securing-critical-infrastructure [9] Large Language Models Versus Static Code Analysis Tools: A Systematic Benchmark for Vulnerability Detection arXiv · Research · https://arxiv.org/abs/2508.04448 SCA [10] 60 malicious Ruby gems downloaded 275,000 times steal credentials BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/60-malicious-ruby-gems-downloaded-275-000-times-steal-credentials [11] From Beginner to Builder: Understanding OpenSSF Community and Working Groups OpenSSF · Analysis · https://openssf.org/blog/2025/08/08/from-beginner-to-builder-understanding-openssf-community-and-working-groups [12] RubyGems, PyPI Hit by Malicious Packages Stealing Credentials, Crypto, Forcing Security Changes The Hacker News · Research · https://thehackernews.com/2025/08/rubygems-pypi-hit-by-malicious-packages.html [13] Fake WhatsApp developer libraries hide destructive data-wiping code BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/fake-whatsapp-developer-libraries-hide-destructive-data-wiping-code DAST [14] ReFuzzer: Feedback-Driven Approach to Enhance Validity of LLM-Generated Test Programs arXiv · Research · https://arxiv.org/abs/2508.03603 [15] AI Is Transforming Cybersecurity Adversarial Testing - Pentera Founder’s Vision The Hacker News · Analysis · https://thehackernews.com/2025/08/ai-is-transforming-cybersecurity.html AGENTIC SDLC [16] I Spent $500 To Test Devin AI For Prompt Injection So That You Don't Have To Embrace The Red · Research · https://embracethered.com/blog/posts/2025/devin-i-spent-usd500-to-hack-devin [17] Claude Code: Data Exfiltration with DNS (CVE-2025-55284) Embrace The Red · Analysis · https://embracethered.com/blog/posts/2025/claude-code-exfiltration-via-dns-requests [18] Context Engineering for Multi-Agent LLM Code Assistants Using Elicit, NotebookLM, ChatGPT, and Claude Code arXiv · Research · https://arxiv.org/abs/2508.08322 [19] ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants arXiv · Research · https://arxiv.org/abs/2508.03936 REMEDIATION [20] Trend Micro warns of Apex One zero-day exploited in attacks BleepingComputer · Incident · https://bleepingcomputer.com/news/security/trend-micro-warns-of-endpoint-protection-zero-day-exploited-in-attacks [21] Researchers Spot Surge in Erlang/OTP SSH RCE Exploits, 70% Target OT Firewalls The Hacker News · Research · https://thehackernews.com/2025/08/researchers-spot-surge-in-erlangotp-ssh.html [22] Researchers Detail Windows EPM Poisoning Exploit Chain Leading to Domain Privilege Escalation The Hacker News · Research · https://thehackernews.com/2025/08/researchers-detail-windows-epm.html [23] DARPA’s AI Cyber Challenge reveals winning models for automated vulnerability discovery and patching CyberScoop · Analysis · https://cyberscoop.com/darpa-ai-cyber-challenge-winners-def-con-2025 TRUST [24] Never compromise with vulnerabilities: a comprehensive survey on AI governance arXiv · Research · https://arxiv.org/abs/2508.08789 [25] Agentic Frameworks Summary Elastic · Analysis · https://elastic.co/security-labs/blog/agentic-ai-summary [26] Causal Reward Adjustment: Mitigating Reward Hacking in External Reasoning via Backdoor Correction arXiv · Research · https://arxiv.org/abs/2508.04216 [27] Model Context Protocol SEP-1330: Elicitation Enum Schema Improvements and Standards Compliance Model Context Protocol · Proposal · https://github.com/modelcontextprotocol/modelcontextprotocol/issues/1330 MODELS [28] Special-Character Adversarial Attacks on Open-Source Language Model arXiv · Research · https://arxiv.org/abs/2508.14070 [29] FIDELIS: Blockchain-Enabled Protection Against Poisoning Attacks in Federated Learning arXiv · Research · https://arxiv.org/abs/2508.10042 [30] BadPromptFL: A Novel Backdoor Threat to Prompt-based Federated Learning in Multimodal Models arXiv · Research · https://arxiv.org/abs/2508.08040 [31] Multi-Turn Jailbreaks Are Simpler Than They Seem arXiv · Research · https://arxiv.org/abs/2508.07646 AI SECURITY [32] Securing Agentic AI: Threat Modeling and Risk Analysis for Network Monitoring Agentic AI System arXiv · Research · https://arxiv.org/abs/2508.10043 [33] ZombAI Exploit with OpenHands: Prompt Injection To Remote Code Execution Embrace The Red · Analysis · https://embracethered.com/blog/posts/2025/openhands-remote-code-execution-zombai [34] Researchers Uncover GPT-5 Jailbreak and Zero-Click AI Agent Attacks Exposing Cloud and IoT Systems The Hacker News · Research · https://thehackernews.com/2025/08/researchers-uncover-gpt-5-jailbreak-and.html [35] When a Jira Ticket Can Steal Your Secrets Simon Willison · Analysis · https://simonwillison.net/2025/Aug/9/when-a-jira-ticket-can-steal-your-secrets ADVISORIES IN THIS WINDOW 27 Go advisories · 1 critical · 7 high · 15 moderate · 4 low 9 npm advisories · 4 high · 3 moderate · 2 low 8 Maven advisories · 3 high · 5 moderate 7 PyPI advisories · 3 high · 3 moderate · 1 low 5 Multi-ecosystem advisories · 5 critical 5 Packagist advisories · 1 critical · 3 moderate · 1 low 3 crates.io advisories · 1 high · 1 moderate · 1 low 1 RubyGems 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.