grok-imagine-image
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text prompts and reference image data (URLs or Base64) to generate or edit images via an external API.
- Ingestion points: User prompts and reference image data defined in the "Inputs the user might give you" section of SKILL.md.
- Boundary markers: None are defined in the instructions for the API request payload.
- Capability inventory: The skill utilizes curl, Python requests, and Node.js fetch to send data to the gateway.pixazo.ai endpoint as shown in SKILL.md.
- Sanitization: No explicit sanitization or validation of the user-provided prompt is specified.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to fetch additional model-specific parameters and reference documentation from the official vendor website at www.pixazo.ai (SKILL.md).
- [COMMAND_EXECUTION]: The documentation includes a command (npx skills add) for the user to install related skills from the author's official collection (SKILL.md).
Audit Metadata