image-gen
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: Executes a local JavaScript file using the Bun runtime to interface with an image generation API.
- [INDIRECT_PROMPT_INJECTION]: Ingests user-provided text prompts and file paths into shell arguments and API requests. • Ingestion points: The PROMPT and INPUT_IMAGE variables in image-gen.js receive user input via shell arguments. • Boundary markers: No explicit delimiters or instructions are used to separate user input from system instructions within the script's logic. • Capability inventory: The skill has the capability to write files to the local file system (fs.writeFileSync) and perform network requests (fetch). • Sanitization: No input validation or sanitization is performed on the user-provided prompt or file path before usage.
- [DATA_EXFILTRATION]: Reads local files specified by the user to send them to the vendor's internal API (internal.infquest.com) for image processing.
Audit Metadata