aliyun-mps-video-translation
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external media content, such as subtitles and video metadata, which could contain malicious instructions designed to influence the agent's behavior during job configuration or result processing.
- Ingestion points: The skill accepts external OSS or public URIs for subtitles, audio, and video files as defined in
references/fields.md. - Boundary markers: There are no explicit instructions, delimiters, or warnings defined to isolate the agent from potentially malicious content embedded in these external files.
- Capability inventory: The skill performs API calls to Alibaba Cloud media services (
SubmitVideoTranslationJob,GetSmartHandleJob,ListSmartJobs) using the data provided. - Sanitization: The instructions do not specify any validation or sanitization steps for the content retrieved from external URIs before it is processed by the agent.
Audit Metadata