Turn specs into evals for any agent with ASSERT
Adaptive Spec-driven Scoring for Evaluation and Regression Testing (ASSERT) is an open-source framework for converting natural language behavior requirements into executable evaluations of AI models a
Search Intelligence
Reconstructing AI activity in investigations
Learn how to investigate AI activity in Microsoft 365 Copilot and Azure AI services using a structured, telemetry-driven approach. This playbook helps security teams reconstruct events, assess data ex
AI brands as bait: How threat actors are using the AI hype in social engineering
As threat actors operationalize AI to accelerate attacks, they are also leveraging the wider global interest around AI itself as a social engineering lure. The post AI brands as bait: How threat actor
Securing CI/CD in an agentic world: Claude Code Github action case
Microsoft Threat Intelligence identified a prompt injection pathway in Claude Code GitHub Action that allowed access to workflow secrets under specific conditions. This research examines the attack ch
25th May – Threat Intelligence Report
For the latest discoveries in cyber research for the week of 25th May, please download our Threat Intelligence Bulletin. TOP ATTACKS AND BREACHES 7-Eleven, the global convenience store chain, confirme
CIRT insights: How to help prevent unauthorized account removals from AWS Organizations
The AWS Customer Incident Response Team works with customers to help them recover from active security incidents. As part of this work, the team often uncovers new or trending tactics used by various
27th April – Threat Intelligence Report
For the latest discoveries in cyber research for the week of 27th April, please download our Threat Intelligence Bulletin. TOP ATTACKS AND BREACHES Vercel, a frontend cloud platform, has disclosed a s
mquire: Linux memory forensics without external dependencies
If you’ve ever done Linux memory forensics, you know the frustration: without debug symbols that match the exact kernel version, you’re stuck. These symbols aren’t typically installed on production sy
Unmasking the Attacker and Decoding Threat Actor Patterns
Contextual visibility into the patterns and activities of threat actors streamlines investigations and helps your organization build proactive defenses against cyber and physical attacks. The post Unm