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 19 September 2025 · Retrospective · Covers 18 September 2025 00:00 to 19 September 2025 00:00 UTC

Read on the web

Top developments

New attack on ChatGPT research agent pilfers secrets from Gmail inboxes

Ars Technica: Security · Incident · AI Security

PyPI invalidates tokens stolen in GhostAction supply chain attack

BleepingComputer · Incident · SCA

SilentSync RAT Delivered via Two Malicious PyPI Packages Targeting Python Developers

The Hacker News · Research · SCA

SAST

LLM-Driven SAST-Genius: A Hybrid Static Analysis Framework for Comprehensive and Actionable Security

arXiv · Research · Remediation, SAST

SecureFixAgent: A Hybrid LLM Agent for Automated Python Static Vulnerability Repair

arXiv · Research · Agentic SDLC, Remediation, SAST

ATLANTIS: AI-driven Threat Localization, Analysis, and Triage Intelligence System

arXiv · Research · DAST, Remediation, SAST

SCA

What Gets Measured Gets Managed: Mitigating Supply Chain Attacks with a Link Integrity Management System

arXiv · Research · SCA

DAST

Orion: Fuzzing Workflow Automation

arXiv · Research · DAST

Evaluating the Effectiveness of Coverage-Guided Fuzzing for Testing Deep Learning Library APIs

arXiv · Research · DAST

Agentic SDLC

5 ways to integrate GitHub Copilot coding agent into your workflow

GitHub · Analysis · Agentic SDLC

Remediation

WatchGuard warns of critical vulnerability in Firebox firewalls

BleepingComputer · Analysis · Remediation

Trust

CoSAI Strategic Update September 2025

CoSAI · Analysis · Trust

How CISOs Can Drive Effective AI Governance

The Hacker News · Analysis · Trust

Models

Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction

arXiv · Research · Models

LLM Jailbreak Detection for (Almost) Free!

arXiv · Research · Models

AI Security

Toward a Unified Security Framework for AI Agents: Trust, Risk, and Liability

arXiv · Research · AI Security

Model Context Protocol SEP-1488: securitySchemes in Tool Metadata for Mixed-Auth Servers

Model Context Protocol · Proposal · AI Security

Advisories in this window

  • 5 npm advisories · 4 critical · 1 moderate
  • 1 PyPI advisory · 1 critical

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.