dreamina-canvas-cli-text2video
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for video generation via a command-line interface. It includes robust security guardrails, specifically forbidding the storage of authentication tokens, cookies, or signed URLs in any persistent logs or status files.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied prompts as part of its primary function. It mitigates potential injection risks by instructing the agent to use a separate prompt-refining skill for定稿 (finalization) and to strictly validate all generation parameters against live discovery data provided by the CLI tool.
- [EXTERNAL_DOWNLOADS]: The skill contains instructions to install related components from the author's own repository (full-aigc-skills/dreamina-skills) using npx. These are identified as legitimate vendor resources and do not represent a security risk.
- [COMMAND_EXECUTION]: The skill uses the dreamina-canvas CLI for node creation and task management. These commands are restricted to functional use, and the instructions explicitly prohibit the agent from adding credit-related flags (like --run or --credit-ceiling) without separate, explicit user confirmation managed by a primary core skill.
Audit Metadata