telnyx-webrtc-client-android

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the telnyx-webrtc-android library from the JitPack repository. This is a standard vendor-provided resource for the Telnyx platform.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to how it handles external data.
  • Ingestion points: Untrusted data enters the application context via transcriptUpdateFlow (which receives transcripts from an AI agent) and customHeaders (used for passing variables to the agent) as described in SKILL.md.
  • Boundary markers: The provided code examples lack boundary markers or explicit instructions to the agent to ignore potentially malicious content embedded within the transcripts or metadata.
  • Capability inventory: The skill requests and uses capabilities including internet access (INTERNET), audio recording (RECORD_AUDIO), and foreground service management for phone calls.
  • Sanitization: There is no evidence of input sanitization or validation for the AI-generated transcripts or custom headers before they are processed by the application logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 03:20 AM