pdf

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines workflows to ingest and process external PDF documents, which could contain instructions intended to influence the agent's behavior during extraction or form filling.
  • Ingestion points: scripts/extract_form_field_info.py and scripts/convert_pdf_to_images.py parse external PDF structures and content.
  • Boundary markers: The forms.md file contains explicit instructions and "CRITICAL" warnings for the agent to follow a strict order of operations and perform visual validation.
  • Capability inventory: The skill has the capability to extract text/tables, convert pages to images, and write new or modified PDF files to the local file system.
  • Sanitization: scripts/fill_fillable_fields.py validates requested field IDs and values against a JSON schema extracted from the PDF before applying changes.
  • [DYNAMIC_EXECUTION]: One of the included scripts modifies the behavior of the pypdf library at runtime.
  • Evidence: In scripts/fill_fillable_fields.py, the monkeypatch_pydpf_method function redefines DictionaryObject.get_inherited from the pypdf package during execution.
  • Context: This is a localized runtime modification used to fix a specific bug in pypdf related to selection list field values and does not involve executing code derived from untrusted sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 09:15 AM