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

Weekly, week 28 of 2025 · Retrospective · Covers 1 July 2025 11:00 to 8 July 2025 11:00 UTC

Read on the web

Top developments

Public exploits released for Citrix Bleed 2 NetScaler flaw, patch now

BleepingComputer · Research · Remediation

Hiding Prompt Injections in Academic Papers

Schneier on Security · Research · AI Security

Over 40 Malicious Firefox Extensions Target Cryptocurrency Wallets, Stealing User Assets

The Hacker News · Research · SCA

Critical Vulnerability in Anthropic's MCP Exposes Developer Machines to Remote Exploits

The Hacker News · Research · AI Security

SAST

We Urgently Need Privilege Management in MCP: A Measurement of API Usage in MCP Ecosystems

arXiv · Research · AI Security, SAST

Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization

arXiv · Research · SAST

Rethinking Broken Object Level Authorization Attacks Under Zero Trust Principle

arXiv · Research · SAST, Trust

CoRe: Benchmarking LLMs Code Reasoning Capabilities through Static Analysis Tasks

arXiv · Research · SAST

SCA

Understand your software’s supply chain with GitHub’s dependency graph

GitHub · Analysis · SCA

Dependabot supports configuration of a minimum package age

GitHub · Analysis · SCA

DAST

RVISmith: Fuzzing Compilers for RVV Intrinsics

arXiv · Research · DAST

On the Surprising Efficacy of LLMs for Penetration-Testing

arXiv · Research · DAST

Agentic SDLC

Last Week In AppSec for 08. July 2025

Checkmarx · Analysis · Agentic SDLC

5 ways to transform your workflow using GitHub Copilot and MCP

GitHub · Analysis · Agentic SDLC

EchoLeak (CVE-2025-32711) Show us That AI Security is Challenging

Checkmarx · Analysis · Agentic SDLC

Remediation

Grafana releases critical security update for Image Renderer plugin

BleepingComputer · Analysis · Remediation

Critical Cisco Vulnerability in Unified CM Grants Root Access via Static Credentials

The Hacker News · Analysis · Remediation

Trust

Red Teaming AI Red Teaming

arXiv · Research · Trust

Strategic Alignment Patterns in National AI Policies

arXiv · Research · Trust

Manage artifact attestations with deletion, filtering, and bulk actions

GitHub · Analysis · Trust

Models

Optimus: A Robust Defense Framework for Mitigating Toxicity while Fine-Tuning Conversational AI

arXiv · Research · Models

Q-Detection: A Quantum-Classical Hybrid Poisoning Attack Detection Method

arXiv · Research · Models

CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation

arXiv · Research · Models

Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning

arXiv · Research · Models

AI Security

How Not to Detect Prompt Injections with an LLM

arXiv · Research · AI Security

AI Agent Smart Contract Exploit Generation

arXiv · Research · AI Security

A Systematization of Security Vulnerabilities in Computer Use Agents

arXiv · Research · AI Security

SAMEP: A Secure Protocol for Persistent Context Sharing Across AI Agents

arXiv · Research · AI Security

Advisories in this window

  • 239 npm advisories · 233 critical · 2 high · 3 moderate · 1 low
  • 13 PyPI advisories · 7 high · 6 moderate
  • 6 Packagist advisories · 4 high · 2 moderate
  • 3 Go advisories · 2 high · 1 moderate
  • 2 crates.io advisories · 2 moderate
  • 2 Maven advisories · 2 moderate
  • 1 RubyGems advisory · 1 moderate

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.