GitHub AI Security Agent Finds 24 Android Vulnerabilities Including Account Takeover Flaws
GitHub’s AI security agent found 24 Android flaws, including OsmAnd tracking and Wikipedia account takeover.
GitHub Security Lab said its open-source Taskflow Agent identified 24 vulnerabilities in Android applications using staged, Android-specific audit workflows. In OsmAnd, which has more than 10 million downloads, an exported MapActivity could let a malicious app silently import settings, redirect map and routing requests, and infer a user’s location. In Wikipedia for Android, weak hostname checks on a wikipedia:// deep link and cookie handling could load an attacker page in a WebView and expose Wikimedia usernames and authentication tokens, enabling account takeover. GitHub said large language model findings still require expert validation, and the workflows are public for GitHub Copilot users.
- GitHub’s Taskflow Agent found 24 Android vulnerabilities after staged audits.
- OsmAnd’s exported activity can silently replace settings and expose location.
- Wikipedia suffix checks can load attacker pages and leak Wikimedia cookies.
- Chained bugs could enable account takeover after one malicious link.
- GitHub says results need human review; the workflows are open source.
- Vendors
- GitHub
- Organizations
- GitHub Security LabWikimedia
From the original article
3 min read at cybersecuritynews.comGitHub Security Lab has disclosed that its open-source AI security agent identified 24 vulnerabilities in Android applications, including flaws that could enable covert location tracking in OsmAnd and account takeover attacks against Wikipedia for Android. The findings highlight how targeted AI workflows can help researchers uncover complex mobile logic flaws, while still requiring human validation. […]
By Abinaya · cybersecuritynews.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.