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 21 October 2026 Retrospective Covers 20 October 2026 00:00 to 21 October 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-10-21/ TOP DEVELOPMENTS [1] From Phishing to LLMjacking: Threat Actors Targeting Cloud Billing Accounts for LLM Usage Wiz · Incident · https://wiz.io/blog/from-phishing-to-llmjacking [2] 8 eMudhra certificates are compromised. Here's what you need to know Cloudflare: Security · Incident · https://blog.cloudflare.com/emudhra-certificate-compromise [3] Qilin and INC Ransomware Groups Exploit Palo Alto Networks Flaw to Bypass MFA The Hacker News · Incident · https://thehackernews.com/2026/10/qilin-and-inc-ransomware-groups-exploit.html [4] Hackers Use Autonomous AI Agents to Breach Company Websites, Target Over 1,200 Sites The Hacker News · Incident · https://thehackernews.com/2026/10/hackers-use-autonomous-ai-agents-to.html [5] Critical FortiSIEM Flaw Gets Public Exploit PoC for Unauthenticated Remote Code Execution The Hacker News · Research · https://thehackernews.com/2026/10/critical-fortisiem-flaw-gets-public.html SAST [6] How Much Does the Harness Matter, and for Whom? A Multi-Model Study of Context in LLM-Driven Vulnerability Discovery arXiv · Research · https://arxiv.org/abs/2610.28802 [7] Self-Evolving Static Analysis via LLM Pseudo-Labeling arXiv · Research · https://arxiv.org/abs/2610.30184 [8] Raise or Check? Predicting the Necessity of Additional Fuzzing for Continuous Fuzzing arXiv · Research · https://arxiv.org/abs/2610.27828 SCA [9] Sign Here: Attributing a Source for a More Trustworthy Software Supply Chain arXiv · Research · https://arxiv.org/abs/2610.28794 [10] Dependabot alerts REST API now includes dependency versions GitHub · Analysis · https://github.blog/changelog/2026-10-20-dependabot-alerts-rest-api-now-includes-dependency-versions [11] GitHub package firewall in public preview GitHub · Analysis · https://github.blog/changelog/2026-10-20-github-package-firewall-in-public-preview DAST [12] Introducing pathrunner: An AWS privilege escalation framework Datadog · Standard / policy · https://securitylabs.datadoghq.com/articles/introducing-pathrunner-aws-privilege-escalation-framework AGENTIC SDLC [13] A Concurrent Structured Record Mirrored the Prose It Accompanied: A Pre-Registered Conceptual Replication and Extension of the Hide Pending Tool Call Scenario arXiv · Research · https://arxiv.org/abs/2611.23274 [14] Agentic Verified Optimization of Real-World Software arXiv · Research · https://arxiv.org/abs/2610.30188 [15] Act on Your Behalf, Beyond Your Authorization: Benchmarking LLM Agent Authorization Alignment arXiv · Research · https://arxiv.org/abs/2610.27548 REMEDIATION [16] php2shell: Assessing Elastic detection coverage relevant to CVE-2026-109618 and CVE-2026-109619 Elastic · Analysis · https://elastic.co/security-labs/threat-command/php2shell-php-rce-detection [17] PHP warns admins of two critical flaws, emergency patches coming tomorrow BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/php-warns-admins-of-two-critical-flaws-emergency-patches-coming-tomorrow [18] There's only so much code: the rise in vulnerability numbers Cisco · Analysis · https://blog.talosintelligence.com/theres-only-so-much-code-the-rise-in-vulnerability-numbers TRUST [19] Reusing Assurance Evidence in AI Pipelines: Validity Conditions, a Fail-Closed Release Gate, and a Replay of 714 Public Data Version Control Pipelines arXiv · Research · https://arxiv.org/abs/2610.27672 [20] KNOX: Hardware-assisted Regulatory Sandbox for Generative Models arXiv · Research · https://arxiv.org/abs/2610.27543 [21] The 9 best KnowBe4 alternatives in 2026 Aikido Security · Analysis · https://aikido.dev/blog/knowbe4-alternatives MODELS [22] Behavior Beyond Text: Evaluating Refusal Transfer Failure in LLM Agents arXiv · Research · https://arxiv.org/abs/2610.28982 [23] Black-Box Red-Teaming of Multi-Agent Systems via Reinforcement Learning arXiv · Research · https://arxiv.org/abs/2610.28966 [24] AI Security Literacy: Ecosystem-Based Competency Framework and K-12 Learning Platform arXiv · Research · https://arxiv.org/abs/2610.28859 AI SECURITY [25] Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise arXiv · Research · https://arxiv.org/abs/2610.28810 [26] After the Attacker Leaves: Benchmarking Carryover Attacks on LLM Agents arXiv · Research · https://arxiv.org/abs/2610.28425 [27] Context-Aware Prompt Injection Detection via Small Language Models in RAG Pipelines: nokast-secureRAG arXiv · Research · https://arxiv.org/abs/2610.28364 ADVISORIES IN THIS WINDOW 79 npm advisories · 45 critical · 11 high · 19 moderate · 4 low 28 PyPI advisories · 15 critical · 7 high · 5 moderate · 1 low 5 Maven advisories · 2 high · 3 moderate 1 Packagist advisory · 1 moderate 1 Go advisory · 1 high 1 RubyGems 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.