geo-llms-txt
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves its stated purpose of implementing the llms.txt protocol. All identified behaviors, including file system access for content analysis and the generation of framework-specific code snippets, are within the expected scope of a technical documentation and utility generator.
- [DATA_EXFILTRATION]: The skill reads local source files (Markdown, TSX, HTML) to extract metadata like titles and descriptions. This data is used solely to populate the local llms.txt index files and is not sent to unauthorized external endpoints.
- [COMMAND_EXECUTION]: The instructions provide templates for adding standard build scripts to package.json and creating server-side routes in various web frameworks. These are standard development practices for the intended use case.
- [EXTERNAL_DOWNLOADS]: The skill references the official specification at llmstxt.org and provides manual submission URLs for public directories. No automated downloads or remote code executions were detected.
Audit Metadata