Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill leverages various command-line utilities such as qpdf, pdftotext, pdftk, pdfimages, and pdftoppm for advanced PDF manipulation tasks like merging, splitting, and high-resolution image extraction.
- [PROMPT_INJECTION]: The skill processes external PDF documents, which serves as a potential surface for indirect prompt injection attacks where malicious data within a file could attempt to influence the agent's behavior.
- Ingestion points: PDF files are ingested and processed in scripts/fill_fillable_fields.py, scripts/extract_form_field_info.py, and scripts/convert_pdf_to_images.py.
- Boundary markers: No explicit boundary markers or 'ignore' instructions are used when processing extracted PDF content.
- Capability inventory: The skill has access to file system write operations and shell command execution via CLI tools.
- Sanitization: No sanitization or filtering of PDF-extracted text is performed prior to processing.
- [SAFE]: The script scripts/fill_fillable_fields.py implements a runtime monkeypatch for the pypdf library to resolve a known issue with selection list formatting. This is a localized modification for compatibility and does not execute external or obfuscated code.
Audit Metadata