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, Saturday 8 August 2026 · Retrospective · Covers 7 August 2026 00:00 to 8 August 2026 00:00 UTC

Read on the web

Top developments

More than half of AI-generated patches are broken

CyberScoop · Research · Remediation

TeamPCP Linked To Redis Attacks Dating Back To 2020 And Later Supply Chain Campaign

The Hacker News · Incident · SCA

Metabase SQLi zero-day exploited in customer data-theft attacks

BleepingComputer · Incident

SCA

The security signal log tailing can't see: tracking npm cooldown removals with Elastic Agent

Elastic · Analysis · SCA

Nearly 800 Malicious npm Packages Deliver Cross-Platform RAT and Infostealer

The Hacker News · Analysis · SCA

Agentic SDLC

Living off the coding agent: Two tales of tunnels and LaunchAgents

Elastic · Analysis · Agentic SDLC

Claude Code and Gemini CLI Flaws Let a GitHub Issue Reach CI Workflow Secrets

The Hacker News · Analysis · Agentic SDLC, AI Security

Remediation

New WordPress Pre-Auth XSS Could Lead to PHP Code Execution - Patch ASAP

The Hacker News · Analysis · Remediation

Trust

Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Space

arXiv · Research · Trust

IntelliAudit: Using Large Language Models to Evaluate Audit Controls

arXiv · Research · Trust

Towards Assurance Closure in AI-Native Large-Scale Agile Software Development

arXiv · Research · Trust

Models

Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits

arXiv · Research · Models

LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activation Spikes

arXiv · Research · Models

MITRE ATLAS (releases) v2026.07

MITRE · Release · AI Security, Models

AI Security

The Anatomy of a Prompt Injection: A Component Model for Structured Analysis

arXiv · Research · AI Security

NiyamAI - An Intent-Bound AI Agent with Cryptographically Verifiable Guardrails using Zero-Knowledge Proofs

arXiv · Research · AI Security

SynChain: Inducing Computer-Use Agent Systems to Construct Their Own Attack Chains

arXiv · Research · AI Security

Advisories in this window

  • 206 npm advisories · 199 critical · 1 high · 5 moderate · 1 low
  • 20 PyPI advisories · 10 critical · 6 high · 4 moderate
  • 8 Packagist advisories · 3 critical · 1 high · 4 moderate
  • 2 Go advisories · 1 high · 1 moderate
  • 1 RubyGems advisory · 1 low
  • 1 Maven 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.