seedream
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill communicates exclusively with the Volcengine API (ark.cn-beijing.volces.com), which is a well-known and trusted cloud service provider operated by ByteDance.
- [SAFE]: Sensitive information like API keys are not hardcoded; the script correctly provides options for the user to supply them securely via command-line flags or the VOLC_API_KEY environment variable.
- [SAFE]: Dependencies are managed using standard Python metadata (PEP 723), referencing the well-known and widely trusted 'requests' package from the official PyPI registry.
- [PROMPT_INJECTION]: The skill inherently exposes an attack surface for indirect prompt injection as it processes user-supplied prompts and image references for AI generation.
- Ingestion points: The '--prompt' and '--image' parameters in the 'generate_image.py' script directly ingest untrusted user-controlled data.
- Boundary markers: The script does not implement delimiters or explicit system instructions to prevent the model from obeying instructions embedded within user input.
- Capability inventory: The skill has the capability to perform network POST requests to an external API endpoint.
- Sanitization: There is no validation or sanitization of the user-provided prompt or image data before it is transmitted to the external API.
Audit Metadata