Breaking 23:00 Killer Robots: Guterres Warns of Growing Threat Posed by Autonomous Weapons 22:30 Bharat Semi: Indian Chip Startup Raises $24 Million to Develop AI-Powered Sensors 22:15 Germany: EU Approves UniCredit’s Takeover of Commerzbank in Major Banking Consolidation Move 22:00 Yemen: Riyadh Dismisses Commander of the Military Coalition 21:30 Nvidia: Why Jensen Huang's Departure Could Shake the Entire AI Industry 21:00 Qatar Football: Walid Regragui Emerges as a Leading Candidate for National Team Coaching Job 20:30 Casablanca: Two Minors Sent to Child Protection Centre After Al Jabr School Terror Scare 20:00 Belgium: Romelu Lukaku Announces Retirement From International Football After 16 Years With the National Team 19:30 US Military Reinforcement: Third Aircraft Carrier Arrives in the Middle East Ahead of Trump’s China Summit 19:00 Morocco: Tomato Prices Remain High Despite Suspension of Exports to African Markets 18:30 Yemen: Houthis Advance Within 60 Kilometers of Aden as Government Reinforces Defences 18:00 Happy Passports Index 2026: Morocco Scores 29.7 Points and Ranks 49th 17:30 Casablanca: Building Collapse in Bouchentouf Damages Shops and Three Cars 17:00 AFCON 2027: Morocco Prepare for Crucial Niger Encounter With Qualification in Sight 16:30 South Africa: Seven Western Countries Warn of Rising Kidnapping Threat 16:09 Morocco: ACAPS Seeks Stronger Powers to Prevent Insurance Sector Crises 16:01 Brazil: Carlo Ancelotti Admits More Work Is Needed to Restore the National Team's Competitiveness 16:00 Apple Launches New App: Studying How People Use AI for Health 15:30 Morocco: MP Calls for Cigarette Prices to Reach 100 Dirhams per Pack 15:00 France vs Turkey: Zinédine Zidane Returns to Bordeaux as Les Bleus Secure Nations League Quarter-Final Spot 14:30 South Korea: AI Cheating Fears Prompt Tighter Security Ahead of University Entrance Exam 14:00 AI and Climate Change: UN Warns of Major Opportunities and Growing Environmental Risks 13:45 Israel’s Political Crisis: Eisenkot Accuses Netanyahu of Threatening Democracy 13:30 Anthropic: Three Major Challenges Ahead of Its Potential Stock Market Debut 13:15 GTA VI: Miami Transforms Into Vice City Ahead of the Highly Anticipated Launch 13:00 Morocco: Fuel Prices Drop as Gasoline and Diesel Become Cheaper at the Pump 12:45 Lebanon: US Considers Replacing UNIFIL With Fewer Than 100 International Observers 12:36 OPPO Unveils Photo and AI Innovations in Its New Find X10 Series 12:30 UK: Barrister Suspended for Four Months Over Antisemitic Social Media Posts 12:15 Morocco-US Relations: Mike Waltz to Visit Rabat for Talks on Regional Security and Strategic Cooperation 12:00 Francophonie: Secretary-General Election Postponed by One Year Amid Institutional Reforms 11:45 Amputee Football World Cup 2026: Morocco Beat the United States 2-1 to Reach the Round of 16 10:30 South Africa: Eight Men Shot Dead in KwaZulu-Natal Province 10:15 England: Three Lions Defeat Spain 3-2 in Madrid to End Champions’ Three-Year Unbeaten Run 10:00 Gaza Winter Crisis: Four Nations Demand Entry of 150,000 Tents for Displaced Families 09:56 AS FAR Women: Fouzi Lekjaa Congratulates the Moroccan Club on Its CAF Champions League Triumph 09:45 Angela Merkel: Former German Chancellor Criticizes Disproportionate International Scrutiny of Israel 09:30 Historic Gaza Tour: 20 UN Ambassadors Inspect Hamas Underground Infrastructure 09:15 France-Morocco Security Cooperation: French Police Praise Morocco Following Four Arrests of Internationally Wanted Suspects 09:00 Morocco's Currency Market: Dirham Gains 0.9% Against the Euro as Foreign Reserves Reach MAD 515.6 Billion 08:45 Rwanda: Five European Countries Plan to Establish Migrant Return Centres 08:30 Morocco Weather Forecast for November 16, 2026: Temperatures Reach 35°C in Some Regions

Microsoft AI agent security toolkit flaw exposes missing authentication checks

Monday 27 April 2026 - 10:20
By: Dakir Madiha
Microsoft AI agent security toolkit flaw exposes missing authentication checks

Microsoft faces scrutiny after a security analysis found that authentication checks in its open source AI agent governance toolkit are not executed in production code. The toolkit, released on April 3, was designed to provide runtime safeguards for autonomous AI agents and address risks outlined by OWASP in its top 10 list for agent based systems.

The issue was identified by security researcher Davi Ottenheimer, who examined the codebase and found that authentication primitives exist but are never invoked in operational workflows. Across five language implementations, Rust, Python, TypeScript, .NET, and Go, the verification functions are fully implemented and tested but remain disconnected from production paths. As a result, agent identities are not validated before being processed by governance systems.

Specific implementations reveal practical risks. In the Go version, any caller can impersonate an agent by setting a single HTTP header, allowing unauthenticated identities to pass through governance layers. In the .NET version, actions default to a hard coded anonymous identity when authentication middleware is not configured, leading to audit logs that fail to distinguish between different actors. Core components such as the MCP gateway accept rate limiting and policy engines but do not provide integration points for authentication, leaving verification outside the request flow.

Further analysis shows that some verification functions perform self signed checks that always return true, effectively bypassing identity validation. These mechanisms complete cryptographic steps without establishing trust, creating a false sense of security while leaving systems exposed to impersonation risks.

The findings mirror a separate vulnerability, CVE-2026-32173, affecting an Azure SRE agent developed by Microsoft. Discovered by Yanir Tsarimi of Enclave AI, the flaw allowed any account within the Entra ID ecosystem to access sensitive real time data streams in a multi tenant setup. Microsoft has since patched this issue on the server side.

Researchers describe both cases as part of a broader structural problem in AI security systems, where controls are implemented but not properly integrated. This gap is becoming more critical as companies accelerate adoption of autonomous agents under new regulatory pressure, including the upcoming enforcement of the European Union AI Act and the Colorado AI Act.

Recent industry data shows that 88 percent of organizations have experienced or suspect security incidents involving AI agents, while only 22 percent treat them as independent entities with distinct identities. Experts advise organizations using the toolkit to audit all entry points for agent identity and treat any default anonymous identity in logs as a configuration failure requiring immediate attention.


  • Fajr
  • Sunrise
  • Dhuhr
  • Asr
  • Maghrib
  • Isha

This website, walaw.press, uses cookies to provide you with a good browsing experience and to continuously improve our services. By continuing to browse this site, you agree to the use of these cookies.