Just in:
Thailand’s Most Iconic New Year’s Celebration Returns: ICONSIAM Unveils “Amazing Thailand Countdown 2027” // Yeebo Announces Interim Results for FY26/27 Revenue Increases by 45.5% to HK$806.7 Million Profit Attributable to Owners Surges 87.6% to HK$2,284.7 Million // Sabarimala booking discrepancies prompt sabotage angle probe // Workday targets Honeydew purchase to unify AI metrics // Diabetes Malaysia And Alpro Pharmacy Set National Record With 11,007 Most Blood Glucose Screenings Conducted Across Malaysia In Just 48 Hours // Toward a Shared Future for Humanity: Rethinking Civilizational Exchange // 2026 Tropical Rainforest Ecosystem Partners Conference Kicks off in Hainan // Dar Global unveils $700m Trump development in Qatar // Phancy Announces Business Performance for the Nine Months Ended September 30, 2026 // International Business Leaders Say Xi’s Speech Boosts Confidence in Asia-Pacific Cooperation // Crypto market loses $150 billion amid broad sell-off // Coinbase targets 2027 launch amid state gambling lawsuits // PayerMax and ShopeePay Strengthen Strategic Partnership to Advance Digital Payment Collaboration in Southeast Asia // Padmini follows Padmaja for ‘ghar vapsi’ // Russia permits retail cryptocurrency purchases under regulated framework // Anthropic shares finish above offer price after Nasdaq debut // ED searches five districts in probe against hawala // Sui activates Hashi Bitcoin lending across partner network // Saudi Arabia schedules multinational top-up tax for 2027 // Dubai Introduces SHARH, an AI-Powered Platform Helping Entrepreneurs Buy, Sell and Manage Businesses in the UAE //

Hidden Prompts in GitLab Duo Expose Source Code to Theft

A critical vulnerability in GitLab’s AI-powered coding assistant, Duo, has exposed private source code repositories to theft through a sophisticated indirect prompt injection attack, cybersecurity researchers have revealed. The flaw, now patched, allowed attackers to embed hidden instructions within project content, leading the AI to leak sensitive data and manipulate its responses.GitLab Duo, introduced in June 2023 and built on Anthropic’s Claude models, is designed to assist developers in writing, reviewing, and editing code. However, researchers from Legit Security discovered that Duo’s deep integration across the DevSecOps pipeline made it susceptible to exploitation. By embedding concealed prompts in areas such as merge request descriptions, commit messages, and code comments, attackers could manipulate Duo’s behavior without direct interaction.

The attack exploited Duo’s ability to process and render Markdown content directly in the browser. This feature, while enhancing user experience, introduced client-side injection risks. Malicious actors could inject untrusted HTML into Duo’s responses, potentially redirecting users to phishing sites or executing harmful scripts. In some cases, hidden prompts could instruct Duo to exfiltrate private source code to attacker-controlled servers.

Omer Mayraz, a senior security researcher at Legit Security, emphasized the severity of the vulnerability. “Duo analyzes the entire context of the page, including comments, descriptions, and the source code—making it vulnerable to injected instructions hidden anywhere in that context,” he explained. This comprehensive analysis capability, while beneficial for development, inadvertently expanded the attack surface.

The researchers demonstrated that attackers could further obfuscate malicious prompts using techniques like Base16 encoding, Unicode smuggling, and rendering text in white to evade detection. These methods made it challenging for developers and security tools to identify and mitigate the embedded threats.

Prompt injection, particularly in AI systems, has been recognized as a significant security concern. The Open Worldwide Application Security Project ranked it as a top risk in its 2025 OWASP Top 10 for LLM Applications report. Unlike direct prompt injection, where attackers input malicious commands directly, indirect prompt injection involves embedding harmful instructions within content that the AI processes, making it harder to detect and prevent.

Following responsible disclosure on February 12, 2025, GitLab addressed the vulnerabilities. The company implemented foundational prompt guardrails, including structured prompts, enforced context boundaries, and filtering tools, to reduce the risk of such attacks. However, GitLab acknowledged that while these measures mitigate risks, they do not eliminate all vulnerabilities, especially against sophisticated attacks.



Notice an issue?

Arabian Post strives to deliver the most accurate and reliable information to its readers. If you believe you have identified an error or inconsistency in this article, please don't hesitate to contact our editorial team at editor[at]thearabianpost[dot]com. We are committed to promptly addressing any concerns and ensuring the highest level of journalistic integrity.


Loading next story…
Just in:
European Commission takes systems offline after AI cyberattack // ED searches five districts in probe against hawala // Sabarimala booking discrepancies prompt sabotage angle probe // Oil futures rebound after Riyadh strikes and tanker alerts // LittleLives, Little Lab and SEGi College Sign MOU to Explore Early Childhood Education Collaboration Across ASEAN // Dalilk Academy reaches 27 million, targets 100 million by 2030 // Coinbase targets 2027 launch amid state gambling lawsuits // PayerMax and ShopeePay Strengthen Strategic Partnership to Advance Digital Payment Collaboration in Southeast Asia // Phancy Announces Business Performance for the Nine Months Ended September 30, 2026 // Alibaba shares slip despite 53% cloud revenue growth // Crypto market loses $150 billion amid broad sell-off // Travel Insurance Was Built for the Few Who Claim. Ancileo’s Felt Coverage™ is for Everyone Else // Yeebo Announces Interim Results for FY26/27 Revenue Increases by 45.5% to HK$806.7 Million Profit Attributable to Owners Surges 87.6% to HK$2,284.7 Million // Promoting Common Human Development Through Exchanges and Mutual Learning Among Civilizations // Workday targets Honeydew purchase to unify AI metrics // International Business Leaders Say Xi’s Speech Boosts Confidence in Asia-Pacific Cooperation // 2026 Tropical Rainforest Ecosystem Partners Conference Kicks off in Hainan // Saudi Arabia schedules multinational top-up tax for 2027 // Thailand’s Most Iconic New Year’s Celebration Returns: ICONSIAM Unveils “Amazing Thailand Countdown 2027” // Sharjah clears Kalba free zone plan for 400MW complex //