alicloud-media-video-translation-test
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script
tests/common/compile_skill_scripts.pyto perform an offline compilation check on the target skill's directory. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting the content of an external
SKILL.mdfile to decide which API actions to perform. - Ingestion points:
skills/media/video/alicloud-media-video-translation/SKILL.md. - Boundary markers: No delimiters or ignore instructions are present to protect against malicious content in the external file.
- Capability inventory: The skill has the capability to execute cloud API calls based on findings in the processed data.
- Sanitization: No explicit sanitization, validation, or filtering of the parsed API endpoints is mentioned before the call is executed.
Audit Metadata