This paper addresses the limited attention given to blind users as content creators in Content Management Systems (CMS), a gap that remains under-explored in web accessibility research. For blind authors, effective interaction with CMS platforms requires more than technical compliance; it demands interfaces designed with semantic clarity, predictable navigation, and meaningful feedback for screen reader users. This study investigates the accessibility barriers blind users face when performing key tasks, such as page creation, menu editing, and image publishing, using CMS platforms. A two-fold evaluation was conducted using automated tools and manual usability testing with three blind and one sighted participant, complemented by expert analysis based on the Barrier Walkthrough method. Results showed that block-based interfaces were particularly challenging, often marked as accessible by automated tools but resulting in critical usability issues during manual evaluation. The use of a text-based editor, the integration of AI-generated image descriptions, and training aligned with screen reader workflows, significantly improved usability and autonomy. These findings underscore the limitations of automated assessments and highlight the importance of user-centered design practices. Enhancing CMS accessibility requires consistent navigation structures, reduced reliance on visual interaction patterns, and the integration of AI tools that support blind content authors throughout the content creation process.

15 pages, 5 figures, presented in Ibero-American Conference on Human-Computer Interaction 2025