video-avatars-and-virtual-backgrounds
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a potential surface for indirect prompt injection as it is designed to process and analyze user-provided code repositories and technical requests related to video processing.
- Ingestion points: User-provided repositories, existing code snippets, or natural language requests regarding WebRTC and MediaPipe implementations.
- Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the processed data.
- Capability inventory: The skill is limited to providing architectural plans and minimal JavaScript/TypeScript snippets for client-side processing (WebGL, WebGPU, WebRTC); it lacks capabilities for file system modification, shell command execution, or network exfiltration.
- Sanitization: No specific sanitization or escaping protocols are provided for handling external content.
- [SAFE]: The skill references legitimate vendor resources belonging to 'tippyentertainment', including its official GitHub repository and the associated 'tasking.tech' platform domain. These are used for identification and context and do not involve suspicious downloads or configurations.
Audit Metadata