twilio-admin

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads installation scripts from NodeSource and packages from official registries (NPM, PyPI) to set up the Twilio CLI and Python SDK. These are standard procedures from well-known technology providers.
  • [COMMAND_EXECUTION]: Provides detailed instructions and scripts for executing shell commands via the Twilio CLI and system utilities (curl, jq) to perform administrative tasks like account suspension and number management.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted data (such as account friendly names and usage descriptions) from the Twilio API.
  • Ingestion points: Account data ingested via twilio api:core:accounts:list and the twilio-python SDK's list methods in SKILL.md.
  • Boundary markers: The provided scripts do not utilize boundary markers or instructions to disregard embedded commands in the retrieved data.
  • Capability inventory: The skill has capabilities to execute CLI commands and make network requests based on its administrative purpose.
  • Sanitization: There is no evidence of sanitization or validation performed on the strings retrieved from the Twilio API before they are processed or displayed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 05:45 PM