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, Friday 6 February 2026 · Retrospective · Covers 5 February 2026 00:00 to 6 February 2026 00:00 UTC

Read on the web

Top developments

CVE-2026-24423: SmarterTools SmarterMail Missing Authentication for Critical Function Vulnerability added to CISA's Known Exploited Vulnerabilities catalog

CISA · Advisory

$f$-FUM: Federated Unlearning via min--max and $f$-divergence

arXiv · Research · Models

Persistent Human Feedback, LLMs, and Static Analyzers for Secure Code Generation and Vulnerability Detection

arXiv · Research · SAST

DAST

Does Programming Language Matter? An Empirical Study of Fuzzing Bug Detection

arXiv · Research · DAST

Agentic SDLC

Capture the Flags: Family-Based Evaluation of Agentic LLMs via Semantics-Preserving Transformations

arXiv · Research · Agentic SDLC, Models

Continuous AI in practice: What developers can automate today with agentic CI

GitHub · Analysis · Agentic SDLC

Remediation

LLM-discovered 0 days

Anthropic · Analysis · Remediation

Trust

Partnership on AI to Host Enterprise AI Governance Forum with JPMorganChase Ahead of India AI Impact Summit

Partnership on AI · Analysis · Trust

Models

Learning to Inject: Automated Prompt Injection via Reinforcement Learning

arXiv · Research · AI Security, Models

BadTemplate: A Training-Free Backdoor Attack via Chat Template Against Large Language Models

arXiv · Research · Models

Visual Exclusivity Attacks: Automatic Multimodal Red Teaming via Agentic Planning

arXiv · Research · Models

AI Security

Clouding the Mirror: Stealthy Prompt Injection Attacks Targeting LLM-based Phishing Detection

arXiv · Research · AI Security

Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening

arXiv · Research · AI Security

Model Context Protocol SEP-2207: OIDC-flavored refresh token guidance

Model Context Protocol · Proposal · AI Security

Advisories in this window

  • 28 npm advisories · 26 critical · 2 moderate
  • 5 Go advisories · 1 critical · 2 high · 2 moderate
  • 4 PyPI advisories · 2 high · 2 moderate
  • 2 crates.io advisories · 1 high · 1 moderate
  • 2 RubyGems advisories · 2 high
  • 2 Packagist advisories · 2 low

All advisories

Titles, links and short excerpts only; every item links to its source. Selection is automatic; the editor's note is AI-drafted and checked as described. Preview: the unsubscribe link and Keryn's postal address are added to each email when it is sent.