skills/twilio/ai/twilio-cli-reference/Gen Agent Trust Hub

twilio-cli-reference

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documents terminal commands for the Twilio CLI to provision phone numbers, send communications, and manage serverless deployments. This is the primary function of the skill.
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of the twilio-cli and official plugins (from the @twilio-labs namespace) via standard package managers like Homebrew, Scoop, and NPM. It also suggests ngrok for webhook tunneling.
  • [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by instructing the agent to interpolate user-provided content into CLI command arguments (e.g., message bodies or email text).
  • Ingestion points: User-supplied text for SMS and email content in SKILL.md.
  • Boundary markers: None mentioned for the command generation.
  • Capability inventory: Subprocess execution of Twilio CLI commands.
  • Sanitization: Not explicitly defined within the reference documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 04:07 PM
Security Audit — agent-trust-hub — twilio-cli-reference