markitdown-ocr
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill contains legitimate documentation and code samples for document processing.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing standard Python packages (e.g.,
markitdown-ocr,openai,azure-openai) from official registries. It also links to official Microsoft source code repositories on GitHub, which are recognized as trusted sources. - [CREDENTIALS_UNSAFE]: No hardcoded secrets or API keys were discovered. The instructions and code examples correctly emphasize the use of environment variables for managing sensitive credentials.
- [COMMAND_EXECUTION]: Example commands are limited to environment verification and tool usage. The provided Python wrappers for the CLI are standard implementations designed to facilitate user configuration and do not perform dangerous operations.
Audit Metadata