skills/ginlix-ai/langalpha/pptx/Gen Agent Trust Hub

pptx

Warn

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: MEDIUMDYNAMIC_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [DYNAMIC_EXECUTION]: The script scripts/office/soffice.py contains logic to dynamically write, compile, and load a C shared library at runtime. It uses gcc to create a binary (lo_socket_shim.so) in the temporary directory and injects it into the LibreOffice process via the LD_PRELOAD environment variable to shim standard socket system calls.
  • [COMMAND_EXECUTION]: The skill makes extensive use of the subprocess module to execute system-level commands, including soffice for PDF conversion, pdftoppm for image generation, git diff for change tracking, and gcc for runtime compilation.
  • [DATA_EXFILTRATION]: Documentation in pptxgenjs.md describes the use of the addImage function with arbitrary remote URLs (e.g., https://example.com/image.jpg). This allows the agent to initiate outbound network requests to non-whitelisted domains during presentation creation.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided .pptx files. Extracted text from these files (via markitdown) is ingested into the agent's context without explicit boundary markers or sanitization, creating a surface for indirect instructions to influence agent behavior.
  • [EXTERNAL_DOWNLOADS]: The skill requires and documents the installation of several external dependencies from public registries, including pptxgenjs, react-icons, and sharp via NPM, and markitdown and Pillow via PyPI.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 11, 2026, 01:05 AM