pptx-creating

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses subprocess.run() to invoke external utilities such as soffice, pdftoppm, and git for presentation conversion and validation tasks. These commands incorporate user-provided file paths as arguments.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external PowerPoint files, creating a potential surface for indirect prompt injection attacks.
  • Ingestion points: Slide text is extracted via inventory.py and markitdown for analysis and editing.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within presentation text.
  • Capability inventory: The skill possesses capabilities including shell command execution (subprocess.run), filesystem writes, and HTML rendering using a browser environment (playwright).
  • Sanitization: XML data is processed using defusedxml, mitigating common XML-based vulnerabilities such as XXE.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 04:17 PM