Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process text and data from external PDF files, which could contain malicious instructions intended to manipulate the agent's logic.
- Ingestion points: Scripts such as
extract_form_field_info.py,fill_fillable_fields.py, andmerge_pdfs.pyread data from local PDF files using thepypdfandpdfplumberlibraries. - Boundary markers: There are no implementation details for using delimiters or specific system instructions to ignore potential commands embedded within the PDF content.
- Capability inventory: The skill possesses extensive file system capabilities, including reading and writing PDF, image, and Excel files across multiple scripts.
- Sanitization: The skill does not appear to perform sanitization or validation of the text extracted from PDF documents before processing it.
- [COMMAND_EXECUTION]: The skill documentation in
SKILL.mdandreference.mdprovides instructions and examples for executing system-level command-line tools such asqpdf,pdftotext, andpdftk. These operations involve shell execution and should be monitored for unexpected command construction.
Audit Metadata