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 TelnyxRTC library 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 subscribeToTranscriptUpdates callback in SKILL.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
Risk Level
SAFE
Analyzed
Mar 12, 2026, 03:57 AM