Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands and Python scripts to perform PDF operations such as merging, splitting, and form filling. These commands are executed locally through tool-provided interfaces like
uvand are standard for the skill's utility. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external PDF documents for text and structure extraction, which represents an ingestion point for untrusted content. * Ingestion points: PDF data is read using
pypdf,pdfplumber, andpdftotextas described inSKILL.mdandscripts/extract_form_structure.py. * Boundary markers: No specific delimiters or safety instructions for handling extracted text are provided to the agent. * Capability inventory: The agent has local file system access and the ability to execute shell commands viauv. * Sanitization: There is no evidence of sanitization or filtering of the extracted PDF content before it is processed. - [EXTERNAL_DOWNLOADS]: The skill identifies several standard third-party libraries (e.g.,
pypdf,pdfplumber,reportlab,pdf-lib) as dependencies. These are legitimate, industry-standard tools for PDF processing and do not indicate a security risk.
Audit Metadata