workflow-streaming-distribution
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates an Indirect Prompt Injection surface (Category 8).
- Ingestion points: The skill accepts a
[source]argument which can be a remote stream URL or an untrusted local video file. - Boundary markers: There are no explicit boundary markers or instructions to ignore embedded metadata/instructions within the processed media files described in this workflow.
- Capability inventory: The workflow utilizes powerful media processing and system tools including
ffmpeg,gstreamer,aws cli, andrclonevia referenced sub-skills. - Sanitization: No specific sanitization or validation of the input source content is mentioned before it is processed by the encoding pipeline.
Audit Metadata