Daily, Monday 1 December 2025
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.
Top developments
- 1
How Checkmarx Defends Against the Shai-Hulud Second Coming Malicious Package Campaign
On 24 November 2025, news broke of a major attack against the NPM open-source package repository, the primary source of open-source software dependencies used by JavaScript and TypeScript applications. And of course, Checkmarx responded rapidly to keep our customers safe. This…
- 2
Mitigating Indirect Prompt Injection via Instruction-Following Intent Analysis
Indirect prompt injection attacks (IPIAs), where large language models (LLMs) follow malicious instructions hidden in input data, pose a critical threat to LLM-powered agents. In this paper, we present IntentGuard, a general defense framework based on instruction-following…
- 3
On the Regulatory Potential of User Interfaces for AI Agent Governance
AI agents that take actions in their environment autonomously over extended time horizons require robust governance interventions to curb their potentially consequential risks. Prior proposals for governing AI agents primarily target system-level safeguards (e.g., prompt…
Further reading, by topic
Advisories in this window
- 3 PyPI advisories1 high · 2 moderate
- 2 Packagist advisories2 low
- 2 npm advisories2 moderate
This edition
8 developments and 7 advisories in the window. Selection and order are automatic: how stories are placed and ranked.