aliyun-happyhorse-i2v
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides validation steps in the SKILL.md file that utilize common shell commands for directory management and Python syntax checking.
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the requests library, which is a standard, well-known, and trusted Python package for making network requests.
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided text prompts and image URLs (Ingestion points) as input for the video generation process. There are no explicit boundary markers or sanitization logic applied to the prompt (Boundary markers, Sanitization). The skill is capable of writing JSON result files to the local disk and making POST/GET requests to the DashScope API (Capability inventory). These interactions are entirely consistent with the primary purpose of the skill and the expected behavior of an API wrapper.
Audit Metadata