zenstudio
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Installs the
zenstudio-cli@1.3.5package from the npm registry. This is the official command-line interface required for the skill to interact with the ZenStudio platform. - [COMMAND_EXECUTION]: Executes various
zenclicommands via the Bash tool to perform content generation (images and videos), manage project assets, and handle file uploads/downloads. - [CREDENTIALS_UNSAFE]: Documents the storage of API keys in
~/.zencli/config.json. This is standard persistence for the tool's authentication and is not a vulnerability in the skill's logic. - [PROMPT_INJECTION]:
- Ingestion points: Processes user-supplied text prompts for media generation and ingests external data via
nodes.jsonfor canvas updates. - Boundary markers: Commands use standard flag delimiters (e.g.,
--prompt,--file) to separate instructions from user data. - Capability inventory: The skill has the capability to execute shell commands through the
zenclibinary and read local files. - Sanitization: Relies on the ZenStudio API and CLI for input validation; no additional sanitization is implemented within the skill instructions.
Audit Metadata