telnyx-sip-integrations-javascript

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses the official telnyx npm package, which is the authorized SDK for the Telnyx service and maintained by the author.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through several data ingestion points.
  • Ingestion points: External content is introduced into the agent context in SKILL.md via client.recordingTranscriptions.list(), client.externalConnections.logMessages.list(), and client.media.download().
  • Boundary markers: SKILL.md does not include specific boundary markers or instructions to isolate or treat ingested external content as untrusted.
  • Capability inventory: The skill provides a wide range of capabilities in SKILL.md, including SIP trunking configuration, media file management, and the creation or deletion of storage and Dialogflow credentials.
  • Sanitization: No sanitization or validation mechanisms are described or implemented for the external data retrieved by these methods.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 09:56 PM