saas-motion-video

Pass

Audited by Gen Agent Trust Hub on Oct 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on several local scripts to perform its functions, including Python scripts for theme selection (pick_themes.py), variety auditing (variety_audit.py), sound processing (warm_sfx.py), history reporting (history_report.py), and a shell script for delivery (deliver.sh).
  • [EXTERNAL_DOWNLOADS]: The instructions require the installation of the heygen-com/hyperframes skill using npx skills add. This tool, provided by HeyGen (a well-known AI video service), is central to the video generation workflow.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface by reading content from user-provided URLs or documents to act as a "truth source" for video briefs and components.
  • Ingestion points: Stage 1 (Brief) and Stage 2 (Components) process external URLs and documents.
  • Boundary markers: None explicitly defined in the instructions for handling the external content.
  • Capability inventory: The skill can execute local shell and Python scripts, write files (BRIEF.md, STORYBOARD.md), and update a local JSON ledger.
  • Sanitization: There are no explicit instructions to sanitize or escape data retrieved from external sources before it is used to generate prompts or configuration files.
  • [DATA_EXPOSURE]: The skill manages a local file at ~/.motion-ledger.json to track project history. While used for maintaining creative variety, this involves reading from and writing to the user's home directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 4, 2026, 05:39 PM