Wednesday, 8 April 2026

Keryn Headlines

Daily Retrospective

Covers 7 April 2026 00:00 to 8 April 2026 00:00 UTC

Daily, Wednesday 8 April 2026

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 Anthropic's Project Glasswing - restricting Claude Mythos to security researchers - sounds necessary to meSimon Willison

Top developments

  1. 1

    Anthropic's Project Glasswing - restricting Claude Mythos to security researchers - sounds necessary to me

    Anthropic didn't release their latest model, Claude Mythos ( system card PDF ), today. They have instead made it available to a very restricted set of preview partners under their newly announced Project Glasswing . The model is a general purpose model, similar to Claude Opus…

    Simon Willison · Research · 7 April 2026 · Remediation

  2. 2

    ‘GrafanaGhost’ bypasses Grafana’s AI defenses without leaving a trace

    Noma Security researchers used indirect prompt injection to turn Grafana’s own AI into an unwitting courier for sensitive corporate data.

    CyberScoop · Research · 7 April 2026 · AI Security

  3. 3

    SOHO router compromise leads to DNS hijacking and adversary-in-the-middle attacks

    Executive summary Forest Blizzard, a threat actor linked to the Russian military, has been compromising insecure home and small-office internet equipment like routers, then modifying their settings in ways that turn them into part of the actor’s malicious infrastructure.

    Microsoft · Incident · 7 April 2026 · 2 sources

Further reading, by topic

SAST

  1. 4
  2. 5

SCA

  1. 6
  2. 7

    Attacks rewritten: Where malware enters the build

    Chainguard · Analysis · 7 April 2026

DAST

  1. 8

    Why Your Automated Pentesting Tool Just Hit a Wall

    BleepingComputer · Analysis · 7 April 2026

  2. 9

Agentic SDLC

  1. 10

Remediation

  1. 11

Trust

  1. 12
  2. 13
  3. 14

    Auditable Agents

    arXiv · Research · 7 April 2026

Models

  1. 15
  2. 16
  3. 17

AI Security

  1. 18
  2. 19
  3. 20

    ClawLess: A Security Model of AI Agents

    arXiv · Research · 7 April 2026

Advisories in this window

  • 65 npm advisories38 critical · 3 high · 22 moderate · 2 low
  • 11 Maven advisories1 critical · 4 high · 5 moderate · 1 low
  • 7 Go advisories2 critical · 4 high · 1 moderate
  • 6 PyPI advisories1 critical · 2 high · 3 moderate
  • 2 crates.io advisories2 high
  • 1 Packagist advisory1 moderate

All advisories

This edition

39 developments and 92 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.