even-g2-bridge

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface as part of its core functionality as a bridge for user input.
  • Ingestion points: The script scripts/worker.js accepts POST requests containing transcribed voice commands from the Even Realities G2 mobile app.
  • Boundary markers: The forwarded input lacks boundary markers or explicit instructions to the downstream LLM to ignore embedded commands.
  • Capability inventory: The worker script possesses network capabilities to communicate with the OpenClaw Gateway, Anthropic, OpenAI, and Telegram APIs.
  • Sanitization: No input sanitization is performed on the user-provided text before it is sent to external AI providers.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 12:33 PM
Security Audit — agent-trust-hub — even-g2-bridge