skills/snyk/agent-scan/pptx/Gen Agent Trust Hub

pptx

Pass

Audited by Gen Agent Trust Hub on Oct 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses subprocess.run to execute external utilities including soffice (LibreOffice) for document validation and conversion, pdftoppm for creating slide thumbnails, and git for word-level diffing of tracked changes. These calls are used for core functionality and target local files.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided .pptx files by unpacking and reading their XML content, which represents an ingestion surface for indirect prompt injection.
  • Ingestion points: Slide content and metadata extracted from OOXML files in ppt/slides/ and related directories.
  • Boundary markers: Absent; extracted text is provided to the agent without specific delimiters or isolation instructions.
  • Capability inventory: Subprocess execution of conversion tools, file system writes to create/modify presentations.
  • Sanitization: The skill uses defusedxml for secure XML parsing to prevent XXE attacks during unpacking and inventory extraction.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 17, 2026, 09:09 PM