extension-store-assets
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides shell commands to execute a local TypeScript script (
generate.ts) using thebunruntime. The commands include a standard pattern for loading environment variables from a.envfile to provide the necessary API credentials. - [EXTERNAL_DOWNLOADS]: The generator script performs network operations, specifically POST requests to the
openRouter.aiimage generation API. This interaction is central to the skill's purpose of generating visual assets. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external configuration data from a JSON file that includes text prompts for image generation. This represents an attack surface for indirect prompt injection if the configuration file is sourced from an untrusted location.
- Ingestion points: The configuration file path is provided via a command-line argument and read by the
loadConfigfunction inscripts/generate.ts. - Boundary markers: The script does not implement specific boundary markers or delimiters when interpolating prompts into the API request body.
- Capability inventory: The script possesses network access (via
fetch) and file system access (reading configuration, reading reference images, and writing output images). - Sanitization: There is no evidence of sanitization or validation of the prompt strings before they are transmitted to the external image generation service.
Audit Metadata