Warn
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: MEDIUMDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [DYNAMIC_EXECUTION]: The script
scripts/fill_fillable_fields.pyimplements amonkeypatch_pydpf_methodfunction that replacespypdf.generic.DictionaryObject.get_inheritedwith a local implementation at runtime to address a specific bug. This represents dynamic modification of third-party library behavior within the skill environment. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted PDF files, creating a vulnerability surface. 1. Ingestion points: The skill uses
scripts/extract_form_field_info.pyandscripts/convert_pdf_to_images.pyto process external PDF files. 2. Boundary markers: The structured instructions informs.mdprovide a workflow but do not contain explicit commands to ignore instructions embedded within the PDF content or metadata. 3. Capability inventory: The skill has the capability to write files to the filesystem throughscripts/fill_fillable_fields.pyandscripts/fill_pdf_form_with_annotations.py. 4. Sanitization: No evidence of input validation or sanitization of text extracted from or written to the PDF documents was found. - [COMMAND_EXECUTION]: Instructions in
forms.mddirect the agent to execute multiple Python scripts from thescripts/directory using shell commands (e.g.,python scripts/check_fillable_fields <file.pdf>). This behavior relies on the agent platform's execution layer to prevent command injection via malicious characters in user-supplied file paths.
Audit Metadata