Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
pdftoppmcommand (part of the Poppler suite) to render PDF pages into images for visual review. - [PROMPT_INJECTION]: The skill processes untrusted PDF documents through text extraction and rendering, which creates an indirect prompt injection surface.
- Ingestion points: External PDF files processed via
pdfplumberandpypdfas described in SKILL.md. - Boundary markers: None identified; no specific delimiters or warnings to ignore embedded instructions are provided.
- Capability inventory: Execution of system commands (
pdftoppm) and Python code using the specified libraries. - Sanitization: No sanitization, escaping, or validation of the extracted PDF content is specified.
Audit Metadata