video-translate
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the behavior of the translation engine.
- Ingestion points: Data is ingested via
video_url,instruction,vocabulary, andsrt_keyparameters in theSKILL.mdAPI specifications. - Boundary markers: There are no explicit boundary markers or instructions to the agent to ignore embedded commands within the processed data.
- Capability inventory: The skill enables network operations (POST and GET requests) to the HeyGen API endpoint (
api.heygen.com). - Sanitization: The instructions do not specify any sanitization or validation of the input URLs or string parameters before they are passed to the external service.
Audit Metadata