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, Monday 10 August 2026 · Retrospective · Covers 9 August 2026 00:00 to 10 August 2026 00:00 UTC

Read on the web

Top developments

Not an A11y: How Android Accessibility Exposes Mobile AI Agents to Indirect Prompt Injection

arXiv · Research · AI Security, Models

Toward Metacognitive One-Shot Indirect Prompt Injection: Strategy Abstraction Via Outcome-Conditioned Reflection

arXiv · Research · AI Security

Generics-Aware Fuzz Target Generation for Rust Libraries via Structured API Analysis

arXiv · Research · DAST

SAST

SkillsMetric: Mapping the Detection Boundary of Static Analysis for Malicious Agent Skills

arXiv · Research · AI Security, SAST

Models

When Skills Meet Safety: Benchmarking and Characterizing the Adaptive Jailbreak Robustness of Skill-Merged LLMs

arXiv · Research · Models

AI Security

The AI safety test is becoming a safety risk

TechCrunch: Security · Analysis · AI Security

Advisories in this window

  • 2 PyPI advisories · 2 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.