telnyx-api

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to handle untrusted data from external sources as its primary function.
  • Ingestion points: Webhook handlers in SKILL.md, assets/examples/webhook-handler.ts, and references/official-docs/messaging.md receive message text and media URLs from external users.
  • Boundary markers: The provided examples for handling incoming messages do not implement explicit delimiters or instructions to ignore nested commands within the message body.
  • Capability inventory: The skill demonstrates capabilities for network requests (Telnyx API, AWS S3 via boto3, and Bitly API), logic branching based on message content, and local file writing for media processing.
  • Sanitization: No input sanitization or filtering is demonstrated for user-provided text or URLs before they are processed or used in replies.
  • [EXTERNAL_DOWNLOADS]: The documentation references and installs standard libraries from official registries (npm, PyPI, Composer, and NuGet).
  • Notable packages include telnyx, tweetnacl, axios, express, and boto3.
  • These are legitimate dependencies for telephony and cloud storage integrations.
  • [COMMAND_EXECUTION]: The documentation includes standard setup and installation commands.
  • Provides instructions for npm install, pip install, and starting server applications using node or python.
  • No high-risk or arbitrary command execution patterns were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 06:34 PM