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, Thursday 6 August 2026 Retrospective Covers 5 August 2026 00:00 to 6 August 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-08-06/ TOP DEVELOPMENTS [1] Incident Report: unsanctioned agent behaviour during cyber testing Simon Willison · Incident · https://simonwillison.net/2026/Aug/5/incident-report [2] 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 [3] “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 [4] QuickFox Supply Chain Attack Delivers FDMTP Backdoor via Trojanized Windows Installer The Hacker News · Incident · https://thehackernews.com/2026/08/quickfox-supply-chain-attack-delivers.html [5] Veeam, Terraform MCP, Django Patch Critical Flaws, Led by CVSS 10.0 Cross-Tenant Bug The Hacker News · Advisory · https://thehackernews.com/2026/08/veeam-terraform-mcp-django-patch.html SAST [6] 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 [7] Trojanized npm Packages Employ NullReceiver Tactic to Decode C2 IP from Blockchain The Hacker News · Research · https://thehackernews.com/2026/08/trojanized-npm-packages-decode-c2-ip.html [8] Open VSX Removes 77 Malicious Evil Twin Extensions Exfiltrating Developer Data The Hacker News · Analysis · https://thehackernews.com/2026/08/open-vsx-removes-77-malicious-evil-twin.html [9] Claude Mythos 5 Tried to Backdoor a Real Open-Source Project in Testing, Then Vouched for Itself The Hacker News · Analysis · https://thehackernews.com/2026/08/claude-mythos-5-tried-to-backdoor-real.html DAST [10] CRLF-Powered Desync Attacks: Beheading HTTP Streams PortSwigger Research · Analysis · https://portswigger.net/research/crlf-powered-desync-attacks [11] Continuous Offensive Security & AI Pentesting: 20 FAQs Snyk · Analysis · https://snyk.io/blog/continuous-offensive-security-ai-pentesting-20-faqs AGENTIC SDLC [12] Scrouting: Cost-Aware Routing of Coding Agents by Scouting the Repository First arXiv · Research · https://arxiv.org/abs/2608.04804 [13] Towards a Risk Assessment of Malicious Skill Files in Coding Agents arXiv · Research · https://arxiv.org/abs/2608.05223 REMEDIATION [14] Critical Gitea Flaw Let Unauthenticated Attackers Read Server Files via Org-Mode Markup The Hacker News · Advisory · https://thehackernews.com/2026/08/critical-gitea-flaw-let-unauthenticated.html TRUST [15] A few notes on AWS Nitro Enclaves: KMS integration Trail of Bits · Analysis · https://blog.trailofbits.com/2026/08/05/a-few-notes-on-aws-nitro-enclaves-kms-integration [16] Blockchain Empowered Trustworthy Agent Networks: Foundations, Taxonomy, and Future Directions arXiv · Research · https://arxiv.org/abs/2608.04626 MODELS [17] Season: Spectrum-Aware Orthogonal Gradient Refinement for Transfer-Based Adversarial Attacks arXiv · Research · https://arxiv.org/abs/2608.04441 [18] Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle arXiv · Research · https://arxiv.org/abs/2608.04314 AI SECURITY [19] Robust Context-Aware Detection of Malicious Instructions in Text arXiv · Research · https://arxiv.org/abs/2608.05430 [20] Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming arXiv · Research · https://arxiv.org/abs/2608.05108 [21] LoginTrap: Uncovering Task-Agnostic Phishing-Style Indirect Prompt Injection Attacks against LLM-based Web Agents arXiv · Research · https://arxiv.org/abs/2608.04741 ADVISORIES IN THIS WINDOW 501 npm advisories · 477 critical · 7 high · 15 moderate · 2 low 17 Go advisories · 4 high · 10 moderate · 3 low 5 PyPI advisories · 4 critical · 1 high 1 Packagist advisory · 1 moderate 1 Maven advisory · 1 high 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.