grok-imagine-video
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and fetches technical documentation from
www.pixazo.ai. It also includes instructions for users to install related skills usingnpxfrom the author's official repository. These references trace back to the vendor's own infrastructure. - [COMMAND_EXECUTION]: The skill manages user API credentials by writing them to a local configuration file at
~/.pixazo/api-key. It explicitly instructs the agent to set restrictive file permissions usingchmod 600, which is a security best practice to prevent other users on the system from reading the key. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external model documentation at runtime to resolve API parameter names and expected values.
- Ingestion points: Fetches markdown documentation from
https://www.pixazo.ai/models/grok-imagine-video.md. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are provided for the fetched content.
- Capability inventory: The skill can perform network requests (POST/GET) and write to the local file system.
- Sanitization: No explicit sanitization of the fetched documentation is described.
Audit Metadata