create-image-gpt-image-fal
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill communicates with fal.ai endpoints to upload reference images and retrieve generated image files. As fal.ai is a well-known service for AI model hosting and this behavior is essential for the skill's primary function, these operations are considered safe.
- [COMMAND_EXECUTION]: The skill is designed to be invoked via a Python CLI script (scripts/generate.py) that executes shell-level commands for file management and process control.
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user-defined text prompts that are passed to an external image generation service. This creates an attack surface for indirect prompt injection, where malicious instructions could be embedded in the processed data.
- Ingestion points: The generate.py script takes input via the --prompt and --ref-image command-line arguments.
- Boundary markers: There are no explicit boundary markers or 'ignore instructions' directives used when constructing the payload for the external API.
- Capability inventory: The script possesses the ability to read local files, write to the filesystem, and perform network requests to external services.
- Sanitization: The input prompts are passed to the API without sanitization or validation.
Audit Metadata