apiyi-gpt-image-2-all-gen
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of local utility scripts (scripts/generate_image.js and scripts/generate_image.py) to process user image generation requests via shell commands.\n- [EXTERNAL_DOWNLOADS]: The included scripts perform network requests to api.apiyi.com and download image data from external URLs to save them locally, which is the core function of the skill.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input that is forwarded to an external AI model, creating an attack surface.\n
- Ingestion points: The -p/--prompt and -i/--input-image CLI arguments in scripts/generate_image.js and scripts/generate_image.py accept arbitrary user-provided text and files.\n
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat user input as non-executable data when constructing the JSON API payloads.\n
- Capability inventory: The skill possesses network access capabilities (https.request and requests.post) and filesystem write access (fs.writeFileSync and Path.write_bytes) across all scripts.\n
- Sanitization: No input validation, escaping, or filtering mechanisms are implemented for the prompts or image data before they are transmitted to the external service.
Audit Metadata