uBlock Origin patches universal XSS bug found via AI-assisted research
A researcher used GPT-5.6 Sol to identify a one-click universal cross-site scripting vulnerability in uBlock Origin's Manifest V2 Firefox build, later confirming a related but less severe issue in the MV3 version, uBO Lite. The flaw let a malicious website manipulate the extension's element picker feature to inject arbitrary trusted filters, which could then run JavaScript in the context of any other site; the issue has since been fixed and documented in a GitHub security advisory.
GoKawiil's interpretation of the reporting above, not reported fact.
The vulnerability shows how a popular browser extension's own content-blocking powers—trusted filters capable of injecting code—can be turned into an attack vector if an attacker can trick its UI into creating one. The disclosure also illustrates a growing pattern of AI tools being used to find real-world security flaws in widely deployed software, which could speed up vulnerability discovery for both researchers and attackers alike.
- uBlock Origin's MV2 Firefox version had a universal XSS flaw via its element picker feature, now patched.
- The MV3 'uBO Lite' version had a related, less severe version of the same issue.
- AI assistance (GPT-5.6 Sol) helped locate the vulnerability, with human researchers verifying and building a proof-of-concept.
Source: iter.ca, 2026-11-16
Published there as: “Universal XSS in uBlock Origin from website-driven element picker”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.