PDF Text Extraction
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Downloads and installs the
asta-pluginspackage from the author's official GitHub repository (github.com/allenai/asta-plugins.git).\n- [COMMAND_EXECUTION]: Executes standard file management commands (mktemp,mv,rm) and uses theastaCLI for processing documents.\n- [DATA_EXFILTRATION]: Facilitates access to AWS S3 buckets for document storage and retrieval, relying on standard AWS credential resolution mechanisms.\n- [SAFE]: While the skill processes untrusted PDF data (Ingestion: PDF files; Capabilities: Bash, Read/Write; Boundary/Sanitization: N/A), this behavior is intrinsic to the skill's primary purpose of OCR and text extraction.
Audit Metadata