zenstudio
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
zenstudio-clipackage from the npm registry during the setup process to enable access to the ZenStudio platform. - [COMMAND_EXECUTION]: The skill relies on the
Bashtool to executezenclicommands for project management, file operations, and AI generation, including a feature to call other MCP tools. - [PROMPT_INJECTION]: The skill processes untrusted external data which could potentially contain malicious instructions, creating a surface for indirect prompt injection.
- Ingestion points: The skill ingests user-provided text prompts for image and video generation, external asset URLs, and canvas node definitions in JSON format.
- Boundary markers: None identified; the instructions do not specify the use of delimiters or 'ignore' instructions for the processed content.
- Capability inventory: The skill has access to the
Bashtool for shell command execution, network access via the CLI, and file system read/write capabilities for project management. - Sanitization: There are no explicit instructions for the validation, filtering, or sanitization of the generative prompts or canvas data processed by the tool.
Audit Metadata