skills/kortix-ai/suna/pdf/Gen Agent Trust Hub

pdf

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill includes instructions to download font files from Google's official GitHub repository (github.com/google/fonts) to support custom typography in generated documents.
  • [COMMAND_EXECUTION]: Documentation and scripts reference the use of established system utilities for PDF manipulation, including qpdf, pdftotext, pdftoppm, pdfimages, and magick. These tools are used for document rendering, text extraction, and structure repair.
  • [PROMPT_INJECTION]: The skill processes external, untrusted PDF files. This creates an attack surface for indirect prompt injection, where malicious instructions embedded in a PDF's text or metadata could attempt to influence agent behavior during extraction or processing tasks.
  • [REMOTE_CODE_EXECUTION]: No patterns of remote script execution or execution of untrusted binary data were detected. File downloads are limited to non-executable assets like fonts from verified sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 04:26 PM
Security Audit — agent-trust-hub — pdf