Microsoft Azure DevOps MCP Flaw Lets Hidden PR Comments Hijack AI Review Agents

July 22, 2026
No Comments

Microsoft Azure DevOps MCP Flaw Lets Hidden PR Comments Hijack AI Review Agents

A single invisible comment in an Azure DevOps pull request can turn a reviewer’s own AI coding agent against them, driving it into projects the attacker has no rights to reach and quietly leaking what it finds.

The flaw is in Microsoft’s official Azure DevOps MCP server, and it works because one of its tools returns pull request descriptions without a prompt-injection guardrail the company had

Leave a Reply Cancel reply

Americans are ignoring scam calls, but phishing emails still fool many July 15, 2026
Americans are becoming more effective at avoiding spam calls and texts, but new research suggests that the strategy comes with an unexpected cost. A new survey of 1,000 Americans from privacy company Cloaked, revealed that two-thirds of respondents have missed an important phone call because they ignored an unknown number. One in three have missed […]
Kirsten Doyle
Sysdig uncovers first documented agentic ransomware operation July 10, 2026
Security researchers at Sysdig have documented what they believe is the first documented case of an AI agent running a ransomware operation from end to end. Dubbed JADEPUFFER, the operation used a large language model (LLM) to automate an attack that began with the exploitation of an internet-facing Langflow instance and ended in destructive database […]
Kirsten Doyle
AI-assisted software engineering is creating a new delivery paradox July 10, 2026
AI can generate code faster than most software organizations can absorb it. This should be a productivity breakthrough, but it also exposes a larger problem: many of the processes surrounding software delivery still happen at human speed. A new white paper from code4thought looks at what happens when AI changes how quickly teams write software, […]
Kirsten Doyle
Filigran report: Organisations can see their threats but can’t act fast enough July 10, 2026
Fragmented tools and manual processes are widening the gap between threat awareness and effective CTEM. Only 41% of organisations have a fully consolidated view of cyber risk exposure, and security teams spend 42% of their time investigating risks that turn out to be low priority or non-exploitable At the same time, AI-driven CTEM processes expected […]
ISB Staff Reporter
The next phase of endpoint security starts with simplicity June 24, 2026
For years, enterprise endpoints were expected to handle everything locally, including productivity, collaboration, storage, and security, while supporting increasingly complex operating systems and applications. But as more workloads have moved into cloud-delivered environments, that model has started to break down. Today’s employees work across virtual desktops, web applications, browsers, and collaboration platforms from virtually anywhere. […]
Kevin Greenway
Klue supply chain breach exposes Salesforce data at several security firms June 24, 2026
A supply chain attack targeting Klue, a competitive intelligence platform, has lead to the theft of Salesforce data from multiple entities, including several cybersecurity vendors. Klue disclosed that threat actors had gained unauthorized access to part of its integration infrastructure in June after compromising a legacy credential linked to a backend system. “Our investigation determined […]
Kirsten Doyle
What Are AI SOC Agents? Use Cases, Architecture, and the Leading Vendors June 19, 2026
The Alert Volume Problem That Created This Category The SANS 2025 Global SOC Survey found that 85% of SOCs trigger incident response primarily from endpoint alerts, while 42% admit to ingesting all data into their SIEM with no structured plan for retrieval or analysis. Volume has outpaced human capacity, and the gap between alerts fired […]
Katrina Thompson
AI-Powered Attacks Become Top Concern for Security Professionals, New Filigran Survey Reveals June 19, 2026
AI-powered attacks are the biggest cybersecurity concern among security professionals. Forty-one percent identified AI-powered attacks at scale as their biggest security concern, nearly double the number citing supply chain risk (21%) or unknown threats (21%). AI-driven threats and what security professionals are doing about them is also the top concern for nearly one in three […]
Kirsten Doyle
ShinyHunters targets Oracle PeopleSoft customers through critical zero-day June 19, 2026
Oracle has issued a security alert to customers about a critical vulnerability affecting PeopleSoft environments after the notorious threat actor ShinyHunters claimed it used a previously unknown flaw to compromise over 100 entities. The vulnerability CVE-2026-35273 is in Oracle PeopleSoft PeopleTools, and has a CVSS score of 9.8/10. “Oracle PeopleSoft Enterprise Applications customers may also […]
Kirsten Doyle
SIG report: AI-generated code is linked to twice the security risk and rising technical debt June 11, 2026
AI-supported coding has progressed from experimental to the norm in organizations, yet technical debt, security risks, and costs could be piling up much faster than anyone realizes. This is one of the key takeaways from the Software Improvement Group (SIG) 2026 State of Software report, which analyzed more than 30,000 software systems and more than […]
Kirsten Doyle

Microsoft Azure DevOps MCP Flaw Lets Hidden PR Comments Hijack AI Review Agents

Trojanized Newtonsoft.Json Fork Hides Game-Rigging Code in a Working Library

OpenAI Says Its AI Models Escaped Sandbox, Targeted Hugging Face to Cheat Benchmark

Leave a Reply Cancel reply

[email protected]

Microsoft Azure DevOps MCP Flaw Lets Hidden PR Comments Hijack AI Review Agents

Microsoft Azure DevOps MCP Flaw Lets Hidden PR Comments Hijack AI Review Agents

Share :

Leave a Reply Cancel reply