Tuesday, 16 September 2025

Keryn Headlines

Daily Retrospective

Covers 15 September 2025 00:00 to 16 September 2025 00:00 UTC

Daily, Tuesday 16 September 2025

Reconstructed on 19 November 2026 from archived source metadata.

From the editor

The editor's note for this issue is not available. The developments below were selected and ranked automatically from the sources listed.

1 When ‘minimal impact’ isn’t reassuring: lessons from the largest npm supply chain compromiseCyberScoop

Top developments

  1. 1

    When ‘minimal impact’ isn’t reassuring: lessons from the largest npm supply chain compromise

    Commentary that downplays the compromise’s impact misses the point, the co-founder of Sonatype argues.

    CyberScoop · Incident · 15 September 2025 · SCA

  2. 2

    Bypassing AI Agent Defenses With Lies-In-The-Loop

    Lies-in-the-loop is a new attack that bypasses AI agent’s “human-in-the-loop” defenses to run malicious code on user machines. Learn what it does and how we uncovered it.

    Checkmarx · Research · 15 September 2025 · AI Security

  3. 3

    Early Approaches to Adversarial Fine-Tuning for Prompt Injection Defense: A 2022 Study of GPT-3 and Contemporary Models

    This paper documents early research conducted in 2022 on defending against prompt injection attacks in large language models, providing historical context for the evolution of this critical security domain. This research focuses on two adversarial attacks against Large Language…

    arXiv · Research · 15 September 2025 · AI Security, Models

Further reading, by topic

SAST

  1. 4

SCA

  1. 5

DAST

  1. 6

    Risky Biz Soap Box: runZero shakes up vulnerability management

    Risky Business · Analysis · 15 September 2025

Remediation

  1. 7

    Microsoft says Windows September updates break SMBv1 shares

    BleepingComputer · Analysis · 15 September 2025

Trust

  1. 8

    Shaping Global AI Governance at the 80th UNGA

    Partnership on AI · Analysis · 15 September 2025

Models

  1. 9
  2. 10

AI Security

  1. 11

    The Risks of Code Assistant LLMs: Harmful Content, Misuse and Deception

    Palo Alto Networks · Analysis · 15 September 2025

Advisories in this window

  • 121 npm advisories107 critical · 10 high · 4 moderate
  • 10 Go advisories3 critical · 3 high · 3 moderate · 1 low
  • 8 Maven advisories6 moderate · 2 low
  • 4 crates.io advisories3 high · 1 moderate
  • 2 PyPI advisories1 critical · 1 moderate
  • 1 Packagist advisory1 moderate
  • 1 Hex advisory1 high

All advisories

This edition

17 developments and 147 advisories in the window. Selection and order are automatic: how stories are placed and ranked.

Follow Keryn Headlines

Security news for teams building with AI. Choose an edition:

  • Daily: Every morning, 06:00 UTC. A short operational briefing: the few developments that matter, who is affected and what to watch. RSS feed
  • Weekly: Tuesdays, about 07:00 US Eastern. The week in order of importance. An editor’s essay accompanies the edition when it passes editorial checks. RSS feed
  • Monthly: The first Tuesday of the month, about 07:00 US Eastern. The month in review. A long read accompanies the edition when it passes editorial checks. RSS feed

Email is not open yet

Use RSS now: it works in any feed reader and needs no sign-up. Add the feed for the edition you want.

Daily feedWeekly feedMonthly feed All editions

When email opens, this box will let you choose editions and confirm by email. Nothing is collected before then.