seedance-2-0-reference-to-video

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is a functional integration for the Seedance 2.0 video generation service. It implements security best practices by setting restrictive file permissions (0600) on its local configuration file to protect API keys.
  • [EXTERNAL_DOWNLOADS]: The script videogen.py downloads generated video and image files from the AI Hive service's API results to the local filesystem.
  • [COMMAND_EXECUTION]: The skill uses a Python-based CLI (videogen.py) to orchestrate API requests, media uploads, and task management.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied strings as prompts for video generation.
  • Ingestion points: User input provided via the --prompt argument in scripts/videogen.py.
  • Boundary markers: None; the prompt is passed directly to the API payload.
  • Capability inventory: The script performs network requests (requests) and file writing (download_file).
  • Sanitization: No specific sanitization is performed on the prompt text before transmission.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 02:00 PM