pdf

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill processes untrusted PDF files (via extract_form_field_info.py and extract_form_structure.py) which may contain instructions intended to manipulate agent behavior. Ingestion points: Reads PDF data and labels. Boundary markers: Absent. Capability inventory: File reading, writing, and image generation. Sanitization: Relies on standard library parsing without explicit content filtering.
  • [Dynamic Execution] (LOW): The script fill_fillable_fields.py performs a runtime monkeypatch of the pypdf library's get_inherited method. This is a dynamic modification of library logic used to ensure compatibility with specific PDF form structures and does not execute arbitrary user input.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 04:38 AM