Telnyx Cli

• Outcome: Review
• Latest audit: May 28, 2026 at 11:01 AM UTC
• Version:
  1.1.0

Overview

This appears to be a legitimate Telnyx CLI skill, but it needs review because it can spend money, send messages, manage phone numbers, and handle API keys without strong safety boundaries.

Install only if you are comfortable letting an agent operate your Telnyx account. Require explicit approval before sending messages, buying or releasing numbers, retrying webhooks, creating or refreshing API keys, or starting upgrade flows. Protect the Telnyx API key file, avoid exposing account details in logs, and use consented recipients and secure storage for any exported data.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (4)

Missing User Warnings

Medium

• Confidence: 84% confidence
• Finding: The README tells users to paste an API key during setup without any guidance on secure credential handling, which can normalize unsafe practices such as exposing secrets in shared terminals, shell history, logs, or screenshots. In an agent/CLI context, this is more dangerous because users may run setup in automated or observed environments where credentials can be captured and reused for full account access.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The skill includes examples for purchasing and releasing phone numbers without any guidance to require explicit user confirmation before executing account-changing actions. In an agent context, these commands can spend money, deprovision resources, or disrupt service if the model treats examples as ready-to-run workflows.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The bulk messaging script demonstrates automated sending to a recipient list with no warning about consent, charges, abuse controls, or privacy implications. In an agent skill, this can normalize mass outbound messaging and increase risk of spam, unexpected cost, or messaging unauthorized real users.

Missing User Warnings

Low

• Confidence: 86% confidence
• Finding: The export examples write call and number data directly to local files without warning that the output may contain sensitive account metadata, phone numbers, or call records. In shared or multi-user environments, this increases risk of unintended local disclosure or insecure retention.

VirusTotal

64/64 vendors flagged this skill as clean.