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 2026 Retrospective Covers 4 August 2026 11:00 to 11 August 2026 11:00 UTC Web: https://keryn.dev/headlines/weekly/2026-W33/ TOP DEVELOPMENTS [1] ChainDrop supply chain compromise: Anatomy of a self-propagating worm Microsoft · Incident · https://microsoft.com/en-us/security/blog/2026/08/04/chaindrop-supply-chain-compromise-anatomy-self-propagating-worm [2] BdThemes plugins supply-chain hack creates rogue WordPress admins BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/bdthemes-plugins-supply-chain-hack-creates-rogue-wordpress-admins [3] CISA: SonicWall SMA1000 flaws now exploited by ransomware gangs BleepingComputer · Incident · https://bleepingcomputer.com/news/security/cisa-sonicwall-sma1000-flaws-now-exploited-by-ransomware-gangs [4] Incident Report: unsanctioned agent behaviour during cyber testing Simon Willison · Incident · https://simonwillison.net/2026/Aug/5/incident-report [5] Anthropic’s AI used fake identities, malware in rogue attack on GitHub project Ars Technica: Security · Incident · https://arstechnica.com/security/2026/08/anthropics-ai-used-fake-identities-malware-in-rogue-attack-on-github-project SAST [6] SkillsMetric: Mapping the Detection Boundary of Static Analysis for Malicious Agent Skills arXiv · Research · https://arxiv.org/abs/2608.08468 [7] RustGo: Fairly Directed Greybox Fuzzing for Enforcing Rust Memory Safety arXiv · Research · https://arxiv.org/abs/2608.05870 [8] Agent-Based Test Assertion Generation via Diverse Perspective Aggregation arXiv · Research · https://arxiv.org/abs/2608.05822 [9] Hidden Ciphers and Where to Find Them: Static Discovery and Assessment of Cryptographic Assets in Software arXiv · Research · https://arxiv.org/abs/2608.04857 SCA [10] Massive supply-chain attack compromises 440 packages under four hours CyberScoop · Incident · https://cyberscoop.com/supply-chain-attack-malware-mini-shai-hulud-teampcp [11] Massive ChainDrop npm supply-chain attack infects hundreds of packages BleepingComputer · Incident · https://bleepingcomputer.com/news/security/massive-chaindrop-npm-supply-chain-attack-infects-hundreds-of-packages [12] TeamPCP Linked To Redis Attacks Dating Back To 2020 And Later Supply Chain Campaign The Hacker News · Incident · https://thehackernews.com/2026/08/teampcp-linked-to-redis-attacks-dating.html [13] “Old Father Eternity”: Shai-Hulud Worm Strikes a 6th Time – keyv/cacheable npm Supply Chain Attack Checkmarx · Incident · https://checkmarx.com/zero-post/shai-hulud-npm-supply-chain-attack-keyv-cacheable DAST [14] OpenAI releases ChatGPT 5.6 Cyber, but it's only for approved users BleepingComputer · Release · https://bleepingcomputer.com/news/security/openai-releases-chatgpt-56-cyber-but-its-only-for-approved-users [15] Show, Don't Tell: What Evo Continuous Offensive Security Found in a Real Enterprise SaaS Snyk · Research · https://snyk.io/blog/what-evo-cos-found-real-enterprise-saas [16] Generics-Aware Fuzz Target Generation for Rust Libraries via Structured API Analysis arXiv · Research · https://arxiv.org/abs/2608.08637 [17] From Documentation to Zero-day Vulnerabilities: LLM-Driven Fuzzing of JavaScript Engines in PDF Readers arXiv · Research · https://arxiv.org/abs/2608.06641 AGENTIC SDLC [18] On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models arXiv · Research · https://arxiv.org/abs/2608.10530 [19] 13 million tool calls: auditing every AI coding agent action with Elastic Agent Elastic · Analysis · https://elastic.co/security-labs/blog/ai-coding-agent-audit-cursor-hooks [20] Activation Probes Surface Code-Security Signals that the Model's Output Misses arXiv · Research · https://arxiv.org/abs/2608.09643 [21] Auto mode is now the default in Claude Code for Pro, Max, and Team plans Simon Willison · Analysis · https://simonwillison.net/2026/Aug/8/auto-mode REMEDIATION [22] CVE-2026-63077: JetBrains TeamCity Deserialization of Untrusted Data Vulnerability added to CISA's Known Exploited Vulnerabilities catalog CISA · Advisory · https://cisa.gov/known-exploited-vulnerabilities-catalog?search_api_fulltext=CVE-2026-63077 [23] More than half of AI-generated patches are broken CyberScoop · Research · https://cyberscoop.com/ai-code-patching-security-risks [24] TP-Link patches Omada ZTP flaws allowing hackers to breach networks BleepingComputer · Advisory · https://bleepingcomputer.com/news/security/tp-link-patches-omada-ztp-flaws-allowing-hackers-to-breach-networks [25] CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training arXiv · Research · https://arxiv.org/abs/2608.06471 TRUST [26] Advance Zero Trust for AI: New tools and guidance to secure AI agents and DevSecOps Microsoft · Standard / policy · https://microsoft.com/en-us/security/blog/2026/08/04/advance-zero-trust-for-ai-new-tools-and-guidance-to-secure-ai-agents-and-devsecops [27] Joint Lyapunov Certificates for K-Agent Generative AI Governance: Stochastic Stability, Emergent Ensemble Risk, and Zero-Knowledge Governance Attestation arXiv · Research · https://arxiv.org/abs/2608.09087 [28] Context Is Not Authority: Structured Runtime Governance for Financial Market Agents arXiv · Research · https://arxiv.org/abs/2608.09025 [29] Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Space arXiv · Research · https://arxiv.org/abs/2608.07786 MODELS [30] Measuring Semantic Abstractness of SAE Features via Nonlocality arXiv · Research · https://arxiv.org/abs/2608.10537 [31] Generating Attacks for LLMs with GFlowNets arXiv · Research · https://arxiv.org/abs/2608.10171 [32] Stealing Reasoning Traces from Proprietary LLM APIs arXiv · Research · https://arxiv.org/abs/2608.09867 [33] Agentic Harnesses: LLM-Driven Verification Layers for Robot Autonomy arXiv · Research · https://arxiv.org/abs/2608.09857 AI SECURITY [34] AI Recommendation Poisoning: How "Ask AI" Buttons Silently Alter LLM Memory The Hacker News · Analysis · https://thehackernews.com/2026/08/ai-recommendation-poisoning-how-ask-ai.html [35] A Gateway Architecture for Enterprise MCP Authentication: Unifying Heterogeneous Auth, Identity Delegation, and the User / Non-User Persona Problem arXiv · Research · https://arxiv.org/abs/2608.10760 [36] From Prompt Injection to Web Exploitation: Revisiting Classic Vulnerabilities in LLM-Integrated Applications arXiv · Research · https://arxiv.org/abs/2608.10281 [37] Why transparent AI agents matter more than you think CyberScoop · Analysis · https://cyberscoop.com/transparent-ai-agent-security-op-ed ADVISORIES IN THIS WINDOW 1396 npm advisories · 1326 critical · 24 high · 42 moderate · 4 low 70 PyPI advisories · 35 critical · 13 high · 20 moderate · 2 low 35 Packagist advisories · 3 critical · 10 high · 19 moderate · 3 low 27 Go advisories · 1 critical · 8 high · 14 moderate · 4 low 6 Maven advisories · 1 critical · 3 high · 2 moderate 1 RubyGems advisory · 1 low 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.