aliyun-zimage-turbo
Warn
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: MEDIUMDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: Accesses sensitive local credential files and environment configurations.
- The script
scripts/generate_image.pyspecifically attempts to read thedashscope_api_keyfrom the path~/.alibabacloud/credentials. - The script also implements logic to search for and load secrets from
.envfiles located in the current working directory or the repository root. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input that is forwarded to an external service without sanitization.
- Ingestion points: User-provided prompts via the
--requestcommand-line argument or JSON files inscripts/generate_image.py. - Boundary markers: None identified; input prompts are directly interpolated into the JSON payload for the external API.
- Capability inventory: The skill possesses network capabilities (HTTPS requests via
urllib.request) and file system write access (saving generated images). - Sanitization: No input validation or output sanitization is performed on the data processed from the remote service.
Audit Metadata