paperbanana-slide-deck

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes several local scripts and CLI tools to manage the slide generation and assembly process, including paperbanana.cli, build-deck.ts, merge-to-pptx.ts, and review-editable.py.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the google-genai Python package, which is an official library provided by a well-known service for interacting with AI models.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided topics, slide counts, and outlines to generate content and image prompts.
  • Ingestion points: Processes content from outline.md, the prompts/ directory, and interactive user input.
  • Boundary markers: Uses --- delimiters within generated prompt files to separate structural style instructions from slide-specific content.
  • Capability inventory: Executes shell commands (via bash blocks), Python scripts, and TypeScript via Bun for merging and building presentations.
  • Sanitization: The skill does not explicitly describe sanitization of the user-provided topic or outline data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 11:21 AM
Security Audit — agent-trust-hub — paperbanana-slide-deck