Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection. It provides instructions and scripts to extract text and metadata from PDF files which are then returned to the agent's context. There are no instructions to use boundary markers or to ignore potential instructions found within the processed PDF content.
- Ingestion points: Text extraction methods using
pypdf,pdfplumber, andpytesseractdescribed inSKILL.mdandreference.md. - Boundary markers: Absent. The skill does not instruct the agent to wrap extracted content in delimiters.
- Capability inventory: The skill includes scripts for file system access (
scripts/fill_fillable_fields.py,scripts/fill_pdf_form_with_annotations.py) and image processing (scripts/convert_pdf_to_images.py). - Sanitization: Absent. There is no evidence of validation or filtering of the extracted text before it is processed by the agent.
Audit Metadata