telnyx-webrtc-client-android

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches its core functionality from the vendor's official GitHub repository via JitPack ('com.github.team-telnyx:telnyx-webrtc-android'). This is a standard dependency for the provided functionality.
  • [PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection within the 'AI Agent Integration' section.
  • Ingestion points: Processes untrusted external data in the form of conversation transcripts via 'telnyxClient.transcriptUpdateFlow' in SKILL.md.
  • Boundary markers: None are implemented in the code snippets to distinguish between instructions and data within the transcripts.
  • Capability inventory: The skill can perform network-based communication actions, including sending automated messages back to the assistant via 'sendAIAssistantMessage' and initiating calls via 'newInvite'.
  • Sanitization: No sanitization, validation, or filtering of the incoming transcript content is shown in the implementation examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 02:55 AM