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, Tuesday 31 March 2026 Retrospective Covers 30 March 2026 00:00 to 31 March 2026 00:00 UTC Web: https://keryn.dev/headlines/daily/2026-03-31/ TOP DEVELOPMENTS [1] Tracking TeamPCP: Investigating Post-Compromise Attacks Seen in the Wild Wiz · Incident · https://wiz.io/blog/tracking-teampcp-investigating-post-compromise-attacks-seen-in-the-wild [2] OpenAI Patches ChatGPT Data Exfiltration Flaw and Codex GitHub Token Vulnerability The Hacker News · Advisory · https://thehackernews.com/2026/03/openai-patches-chatgpt-data.html [3] Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning arXiv · Research · https://arxiv.org/abs/2603.29038 SAST [4] Attesting LLM Pipelines: Enforcing Verifiable Training and Release Claims arXiv · Research · https://arxiv.org/abs/2603.28988 [5] Reachability Across the NL/PL Boundary: A Taxonomy-Driven Dataflow Model for LLM-Integrated Applications arXiv · Research · https://arxiv.org/abs/2603.28345 [6] VulnScout-C: A Lightweight Transformer for C Code Vulnerability Detection arXiv · Research · https://arxiv.org/abs/2603.28309 SCA [7] Wherefore Art Thou? Provenance-Guided Automatic Online Debugging with Lumos arXiv · Research · https://arxiv.org/abs/2603.29013 DAST [8] Detecting and Mitigating Flakiness in REST API Fuzzing arXiv · Research · https://arxiv.org/abs/2603.28452 AGENTIC SDLC [9] Debt Behind the AI Boom: A Large-Scale Empirical Study of AI-Generated Code in the Wild arXiv · Research · https://arxiv.org/abs/2603.28592 REMEDIATION [10] Hackers exploiting critical F5 BIG-IP flaw in attacks, patch now BleepingComputer · Analysis · https://bleepingcomputer.com/news/security/hackers-now-exploit-critical-f5-big-ip-flaw-in-attacks-patch-now [11] Policy-Driven Vulnerability Risk Quantification framework for Large-Scale Cloud Infrastructure Data Security arXiv · Research · https://arxiv.org/abs/2604.06252 TRUST [12] RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems arXiv · Research · https://arxiv.org/abs/2603.28735 [13] "What Did It Actually Do?": Understanding Risk Awareness and Traceability for Computer-Use Agents arXiv · Research · https://arxiv.org/abs/2603.28551 [14] Popular AI gateway startup LiteLLM ditches controversial startup Delve TechCrunch: Security · Analysis · https://techcrunch.com/2026/03/30/popular-ai-gateway-startup-litellm-ditches-controversial-startup-delve MODELS [15] Mitigating Backdoor Attacks in Federated Learning Using PPA and MiniMax Game Theory arXiv · Research · https://arxiv.org/abs/2603.28652 [16] ORACAL: A Robust and Explainable Multimodal Framework for Smart Contract Vulnerability Detection with Causal Graph Enrichment arXiv · Research · https://arxiv.org/abs/2603.28128 [17] Adversarial Attacks on Multimodal Large Language Models: A Comprehensive Survey arXiv · Research · https://arxiv.org/abs/2603.27918 AI SECURITY [18] Evaluating Privilege Usage of Agents with Real-World Tools arXiv · Research · https://arxiv.org/abs/2603.28166 [19] Kill-Chain Canaries: Stage-Level Tracking of Prompt Injection Across Attack Surfaces and Five Production LLMs arXiv · Research · https://arxiv.org/abs/2603.28013 ADVISORIES IN THIS WINDOW 14 Go advisories · 2 critical · 3 high · 8 moderate · 1 low 12 npm advisories · 2 critical · 6 high · 4 moderate 7 Packagist advisories · 1 critical · 1 high · 5 moderate 6 PyPI advisories · 3 critical · 2 high · 1 moderate 4 Maven advisories · 1 critical · 1 high · 2 moderate 2 crates.io advisories · 2 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.