skills/coppermare/skillverse/pptx/Gen Agent Trust Hub

pptx

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted .pptx files, creating an attack surface where embedded data could influence agent behavior. * Ingestion points: Extracts text and XML content from user-provided files using markitdown and internal unpack scripts. * Boundary markers: No specific delimiting or isolation instructions are provided for processed content. * Capability inventory: The skill can execute shell commands, perform filesystem operations, and run Node.js scripts. * Sanitization: Employs defusedxml for secure XML parsing to mitigate XXE risks.
  • [DYNAMIC_EXECUTION]: The presentation creation workflow dynamically generates JavaScript files that are executed using Node.js to interface with the PptxGenJS library.
  • [COMMAND_EXECUTION]: The skill relies on executing various command-line utilities and local scripts (e.g., unpack.py, rearrange.py, soffice, pdftoppm) to manage presentation files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 09:36 AM
Security Audit — agent-trust-hub — pptx