assistant-x-openclaw-jarvis-voice-assistant

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow builds a voice assistant that ingests microphone audio via local ASR and forwards user-spoken commands to an LLM gateway, which inherently processes outsider-submitted free text from voice input.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs cloning an external repository from GitHub (https://github.com/RubinTry/assistant-x-openclaw.git), which constitutes an unverifiable runtime external dependency from an unofficial, individual-owned repository.