add-audio-to-video
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill describes a standard workflow for media processing, focusing on routing user requests to specialized models for sound effects (Mirelo SFX), narration, or music. It correctly identifies sibling skills for tasks outside its primary scope.
- [COMMAND_EXECUTION]: The instructions reference platform-specific tools
runware-runandrunware-modelsfor resolving API schemas and executing inferences. These are vendor-owned tools used for their intended purpose with no evidence of command injection or unsafe execution. - [DATA_EXFILTRATION]: While the skill handles video URLs and UUIDs, this is necessary for its function as a video processing utility. There are no patterns suggesting the unauthorized transfer of sensitive data or credentials.
- [PROMPT_INJECTION]: The skill does not contain any instructions that attempt to bypass AI safety guardrails or override system prompts. It uses natural language to guide the agent through its task without malicious intent.
Audit Metadata