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, Monday 5 October 2026 Retrospective Covers 4 October 2026 00:00 to 5 October 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-10-05/ TOP DEVELOPMENTS [1] Citrix patches NetScaler SAML zero-day exploited in attacks BleepingComputer · Advisory · https://bleepingcomputer.com/news/security/citrix-patches-netscaler-saml-zero-day-exploited-in-attacks [2] CVE-2026-88779: Citrix NetScaler Improper Restriction of Operations within the Bounds of a Memory Buffer Vulnerability added to CISA's Known Exploited Vulnerabilities catalog CISA · Advisory · https://cisa.gov/known-exploited-vulnerabilities-catalog?search_api_fulltext=CVE-2026-88779 [3] Don't Judge an LLM Only by Its Activations: Discovering Suppressed Safety Features via Counterfactual Activation Potential arXiv · Research · https://arxiv.org/abs/2610.05541 AGENTIC SDLC [4] Blocking at the Boundary: Auditing Long-Horizon Agents against Staged Prompt Injection arXiv · Research · https://arxiv.org/abs/2610.05163 [5] Agent Skill Evolution: How Revisions Affect Coding Agents arXiv · Research · https://arxiv.org/abs/2610.04832 REMEDIATION [6] VulValidate: Auditing Function-Level Vulnerability Labels with Executable Evidence arXiv · Research · https://arxiv.org/abs/2610.05103 MODELS [7] Red-TTT: Test-Time Training for Automated Jailbreaking Large Language Models arXiv · Research · https://arxiv.org/abs/2610.05282 [8] Which Image Property Carries the Jailbreak? A Controlled Dissection of Image-to-Text Jailbreaks arXiv · Research · https://arxiv.org/abs/2610.07009 [9] Where Does the Audio Jailbreak Live? A Controlled Frequency-Depth Audit of AdvWave-P on Qwen2-Audio arXiv · Research · https://arxiv.org/abs/2610.07005 AI SECURITY [10] Readable Before Actionable: Causal Tracing of Indirect Prompt Injection arXiv · Research · https://arxiv.org/abs/2610.05295 [11] Who Is Your Agent Serving? Provider-Side Indirect Prompt Injection in Proactive Agents arXiv · Research · https://arxiv.org/abs/2610.05266 [12] Hidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Use arXiv · Research · https://arxiv.org/abs/2610.04985 ADVISORIES IN THIS WINDOW 1 PyPI 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.