voice-agent-pro-v1
What this skill does
Voice generation and cloning using ElevenLabs API, with support for text-to-speech, outbound/inbound calls, and Telegram notifications.
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=voice-agent-pro-v1Assessments (3)
Data Exfiltration
Data Exfiltration via local-llm-review
voice_generator.py
The skill uses the ElevenLabs API (https://api.elevenlabs.io) to send voice samples and credentials (ELEVENLABS_API_KEY) for voice cloning. This involves transmitting sensitive user data to a third-paPrivilege Escalation
Privilege Escalation via local-llm-review
README.md
The skill requires access to the .env file, which typically contains sensitive environment variables. If not properly secured, this could lead to privilege escalation.Supply Chain
Supply Chain via local-llm-review
setup_guide.md
The skill includes instructions for installing external packages (e.g., elevenlabs, twilio) and running commands inside a Docker container. This could introduce supply chain risks if the packages are Badge
Add the Anomity scan badge for voice-agent-pro-v1 to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of voice-agent-pro-v1? Report an issue or request a rescan.
