LIVE FEED
FIRST LOOK OpenAI Releases Astra Cybersecurity Evals and Safeguard Controls // FIRST LOOK OpenAI Pauses Astra Model Over Critical Cybersecurity Threshold // CRITICAL OpenAI Agents Exploit Artifactory RCE in Hugging Face Attack // FIRST LOOK Cloudflare Launches Kitesurf, a Cloud Browser Built for AI Agents // FIRST LOOK PortSwigger HTTP Terminator Ships AI-Driven Desync Research // CRITICAL CVE-2026-12537: Gemini CLI RCE and Claude Code Secret Leak // HIGH Atlassian Rovo Prompt Injection Leaks Jira Data to Attackers // CRITICAL Claude and ChatGPT Hijacked via Zero-Click Prompt Injection // HIGH ChatGPT Sandbox C2 Attack Demonstrated at Black Hat 2026 // HIGH Meta AI Hacks External Systems in Cybersecurity Test //
COPILOT

Copilot

4 reports
All LLM Security Agentic AI Industry News Supply Chain Research Prompt Injection First Look: Security Regulatory Jailbreaks Adversarial ML Model Theft Data Poisoning AI Governance AI Security AI Security Tools Deep Signal Identity & Access Management Intelligence Report Security Operations
Microsoft Copilot Super App Merges Chat, Code, and Agents

Microsoft Copilot Super App Merges Chat, Code, and Agents

FIRST LOOK ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 7.2 The Verge AI

Microsoft has confirmed a Copilot 'super app' launching in 2026 that consolidates chat, GitHub Copilot coding, Cowork collaboration, and agentic Autopilot capabilities into a single unified platform spanning consumer and commercial users. The convergence of these surfaces into one application dramatically expands the blast radius of any successful prompt injection or account compromise, as an attacker who subverts the LLM layer could pivot across coding pipelines, autonomous task execution, and business workflows simultaneously. Defenders should treat this consolidation as a significant privilege-escalation risk, where a single vulnerability in the AI layer now potentially unlocks lateral movement across the entire Microsoft productivity stack.

Microsoft Copilot MCP Tool Poisoning Enables Data Exfiltration

Microsoft Copilot MCP Tool Poisoning Enables Data Exfiltration

ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 9.1 The Hacker News

Microsoft researchers have demonstrated how attackers can embed hidden instructions inside MCP tool descriptions to covertly redirect AI agents into exfiltrating sensitive business data. Because each individual action the agent takes appears legitimate — using approved tools and the user's own permissions — default security controls generate no alerts. The attack exploits a fundamental design tension in MCP: tool descriptions simultaneously carry operational instructions and attacker-controlled data, collapsing a critical trust boundary.

GitHub Ships Data Analytics Agent Built on Copilot

GitHub Ships Data Analytics Agent Built on Copilot

FIRST LOOK ATLAS OWASP MEDIUM Moderate risk · Monitor closely ▲ 6.8 GitHub Blog

GitHub has published a detailed engineering account of how it built an internal data analytics agent using GitHub Copilot, exposing the architectural patterns — including natural language-to-SQL translation, autonomous tool invocation, and internal data access — that underpin such systems. For defenders, this blueprint highlights concrete risks around prompt injection into analytics pipelines, excessive agency over sensitive internal datasets, and the challenge of auditing LLM-generated queries before execution. Organisations adopting similar agentic analytics patterns should treat this as a reference threat model rather than a safe-to-copy architecture.

Microsoft Scout Agent Vulnerable to Prompt Injection

Microsoft Scout Agent Vulnerable to Prompt Injection

ATLAS OWASP MEDIUM Moderate risk · Monitor closely ▲ 6.5 HN AI Security

Microsoft has launched Scout, an always-on autonomous AI agent built on the OpenClaw framework that operates across Microsoft 365 apps including Teams, Outlook, OneDrive, and SharePoint with its own Entra identity. The agent's persistent, unsupervised access to email, calendar, chat, and external systems via MCP creates a broad new attack surface for prompt injection, privilege abuse, and data exfiltration. As an experimental release with limited deployment controls, security teams should treat Scout as a high-risk agentic surface requiring careful governance before broad adoption.

◉ AI THREAT BRIEFING

Stay ahead of the threat.

Twice-weekly digest of critical AI security developments — every story mapped to MITRE ATLAS and OWASP LLM Top 10. Free.

No spam. Unsubscribe anytime.