aliyun-wan-digital-human

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE_&_EXFILTRATION]: The skill uses standard environment variables (DASHSCOPE_API_KEY) and official credential file paths (~/.alibabacloud/credentials) for authentication. This aligns with Alibaba Cloud's recommended security practices and does not involve hardcoded secrets.
  • [COMMAND_EXECUTION]: The skill includes a script scripts/prepare_digital_human_request.py which performs basic file system operations (creating directories and writing JSON files). These operations are scoped to the output/ directory as described in the operational guidance.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of image and audio URLs. While these represent an ingestion surface, the skill simply formats these into a structured JSON payload. There is no evidence of unsafe interpolation or execution of content retrieved from these URLs within the skill's own logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 06:49 AM