Skills
Navigate
skills/full-aigc-skills/dreamina-skills/dreamina-canvas-cli-ref2video/Gen Agent Trust Hub

dreamina-canvas-cli-ref2video

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied prompts and identifiers that are interpolated into shell commands.\n
  • Ingestion points: User-provided values for <prompt>, <projectId>, and local filenames are ingested in SKILL.md, examples/happy-path.md, and examples/first-last-frame.md.\n
  • Boundary markers: Absent. Command templates do not utilize delimiters or safety wrappers for variable inputs.\n
  • Capability inventory: The skill performs shell command execution via the dreamina-canvas CLI (defined in SKILL.md) and conducts file system reads through resource uploading commands (defined in examples/first-last-frame.md).\n
  • Sanitization: Absent. The skill does not define methods for escaping or validating external input before command execution.\n- [COMMAND_EXECUTION]: The skill uses the dreamina-canvas CLI tool for creating video nodes, uploading assets, and querying task status.\n- [EXTERNAL_DOWNLOADS]: The skill references the installation of additional modules from the vendor's repository via the npx skills command.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 01:29 PM