image-studio
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill communicates with an external proxy service at
image-gen-proxy.vercel.app(a well-known cloud platform domain) to perform image generation and token management. - [PROMPT_INJECTION]: The skill processes user-supplied prompts and passes them to external image generation models, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: User input is accepted via the
--promptcommand-line argument intools/generate.jsand transmitted to the remote API. - Boundary markers: No delimiters or safety instructions are used to separate the user-provided prompt from the system-generated enhancements (e.g., style descriptors) before sending the data to the model.
- Capability inventory: The skill possesses network capabilities to send processed data to a remote server via
fetch. - Sanitization: No input validation, escaping, or filtering is performed on the user-supplied prompt string before it is interpolated into the API request payload.
Audit Metadata