frontend-slides

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a Python script to extract content from PowerPoint files and utilizes the 'open' command to launch the resulting HTML presentations in the user's default browser.
  • [EXTERNAL_DOWNLOADS]: The skill depends on the 'python-pptx' library from the official PyPI registry and generates presentations that link to legitimate font services such as Google Fonts and Fontshare.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of untrusted external document formats.
  • Ingestion points: Processes content from PowerPoint (.pptx) files and existing HTML presentations during conversion or enhancement phases.
  • Boundary markers: The skill lacks explicit delimiters or protective instructions when presenting extracted content to the agent for processing.
  • Capability inventory: The skill possesses file-writing capabilities and shell execution (python, open) across its workflow.
  • Sanitization: No sanitization or filtering is applied to extracted slide text, notes, or metadata before they are incorporated into the agent's context or generated output.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:17 PM