improve-aeo-geo
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to modify the user's codebase to implement SEO and AEO optimizations. It targets specific configuration files such as
robots.txt, framework layouts (e.g.,app/layout.tsx,header.php), and content files. This behavior is the primary intended function of the skill and is transparently documented in the workflow. - [SAFE]: The skill incorporates an indirect prompt injection surface by reading and processing external project files which are then used to inform code modifications.
- Ingestion points: Reads local project files across multiple frameworks (Next.js, Nuxt, Astro, SvelteKit, Remix, WordPress, Hugo, Jekyll, 11ty).
- Boundary markers: The skill does not explicitly define delimiters when reading file content into the agent context.
- Capability inventory: The skill has file-write capabilities used to apply audited fixes.
- Sanitization: No explicit content sanitization is described; however, the operations are limited to standard SEO/AEO metadata and structural changes.
- [SAFE]: The skill references a companion website,
aeo-audit.sh, for performance scoring. This is presented as a recommended user-facing tool and does not involve automated data exfiltration or silent background network requests.
Audit Metadata