Skills
skills/elizaos/eliza/voice-call/Gen Agent Trust Hub

voice-call

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill exposes actions that send text messages to voice synthesis engines.
  • Ingestion points: The message parameter in initiate_call, continue_call, and speak_to_user in SKILL.md.
  • Boundary markers: Absent. There are no instructions to the agent to treat input as untrusted data or use delimiters.
  • Capability inventory: Outbound voice communication via Twilio, Telnyx, and Plivo.
  • Sanitization: Absent. The skill does not define any filtering or escaping for the message content.
  • [CREDENTIALS_UNSAFE] (SAFE): While the skill documents configuration keys like authToken and apiKey, no actual secrets are hardcoded in the file.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 06:11 PM