telnyx-webrtc-client-ios
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
TelnyxRTClibrary via CocoaPods and the official Swift Package Manager repository (https://github.com/team-telnyx/telnyx-webrtc-ios.git). These resources originate from the verified vendor 'team-telnyx'. - [PROMPT_INJECTION]: The skill demonstrates integration with an AI Assistant, which creates a surface for indirect prompt injection via data processed from external transcripts.
- Ingestion points: Data enters the application context through the
subscribeToTranscriptUpdatescallback inSKILL.md, which provides a stream of transcripts from the AI assistant service. - Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands implemented in the provided code snippets.
- Capability inventory: The code examples do not demonstrate dangerous capabilities like subprocess execution, file system modification, or arbitrary network requests based on the transcript content.
- Sanitization: The implementation examples do not include sanitization or validation logic for the messages received from the AI assistant.
Audit Metadata