translate-pdf
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content extracted from external PDF files during the translation step. This presents a surface for indirect prompt injection if the PDF contains malicious instructions intended to mislead the agent.
- Ingestion points: The skill reads text content from a source PDF file in Step 4 and 6.
- Boundary markers: No specific delimiters or "ignore" instructions are used when passing the extracted text to the translation phase.
- Capability inventory: The agent has capabilities to execute shell commands (Python scripts, pip) and write files to the local system.
- Sanitization: No sanitization or filtering is performed on the extracted PDF content before processing.
- [COMMAND_EXECUTION]: The skill executes shell commands to run a local Python script for PDF processing and to install necessary dependencies.
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of legitimate, well-known Python packages (pymupdf, markdown, weasyprint) using the system's package manager.
Audit Metadata