aliyun-zimage-turbo
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFECREDENTIALS_UNSAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The Python script
scripts/generate_image.pyis designed to read sensitive authentication data from~/.alibabacloud/credentialsor theDASHSCOPE_API_KEYenvironment variable to authenticate with Alibaba Cloud services. - [DATA_EXFILTRATION]: The skill allows the API endpoint (
base_url) to be overridden via user-provided JSON input. This creates a potential data exfiltration surface where theDASHSCOPE_API_KEYcould be sent to an arbitrary external URL if the input is manipulated by a malicious actor. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8):
- Ingestion points: Untrusted data enters the agent context through the
promptandbase_urlfields in the JSON request passed toscripts/generate_image.py. - Boundary markers: No delimiters or safety instructions are provided to distinguish between system instructions and user-supplied data within the prompts.
- Capability inventory: The skill has the ability to perform authenticated network requests and write files to the local file system.
- Sanitization: The script does not validate the
base_urlparameter to ensure it originates from or targets legitimate Alibaba Cloud domains before sending the authentication token.
Audit Metadata