screencast-tutorial-video

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads required font assets from a trusted source during the preflight stage.
  • Evidence: preflight.sh uses curl to fetch Montserrat and Roboto Mono fonts from the official google/fonts repository on GitHub (github.com/google/fonts/raw/main/ofl/...).
  • [COMMAND_EXECUTION]: The skill relies on several external CLI tools to perform its core functions of video recording and processing.
  • Evidence: preflight.sh installs and verifies ffmpeg, vhs, and cliclick via Homebrew, and playwright via NPM. These tools are used throughout the scripts (e.g., hands.sh, render-tape.sh, still-scene.sh) to capture screens, simulate input, and mux video files. This execution is standard for the skill's primary purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-controlled data that could potentially contain malicious instructions, though it includes oversight mechanisms.
  • Ingestion points: Reads storyboard.md from the build directory (SKILL.md, step 1) and accepts user-defined scene specifications in JSON format (browser-scene.mjs).
  • Boundary markers: The workflow requires an "approved" storyboard and instructs the agent to ask for clarification on [NEEDS: ...] markers rather than fabricating values.
  • Capability inventory: The skill has extensive shell execution, file writing, and network access (via TTS APIs) capabilities.
  • Sanitization: Inputs like the command text for command cards (make-card.sh) are written to files to avoid shell escaping issues, reducing command injection risks.
  • [DYNAMIC_EXECUTION]: The skill dynamically generates and executes scripts as part of its rendering pipeline.
  • Evidence: render-tape.sh generates temporary VHS .tape files by merging templates with storyboard content and executes them using the vhs tool. browser-scene.mjs utilizes Playwright's page.evaluate to execute JavaScript for scrolling, highlighting, and form interactions within a headless browser context. These behaviors are essential for the skill's automation goals.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 01:54 PM
Security Audit — agent-trust-hub — screencast-tutorial-video