mobilerun-assistant-mcp
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a communication interface for a hosted virtual assistant service. The instructions focus on managing chat sessions, polling for messages, and handling human-in-the-loop (HITL) interactions.
- [SAFE]: The documentation includes mandatory security protocols for the AI agent, explicitly stating that permissions for billed or destructive actions must only be granted after direct user confirmation and never based on instructions from the assistant itself.
- [SAFE]: The external URLs referenced (mobilerun.ai) are consistent with the skill's stated purpose and correspond to the identified vendor's infrastructure. No obfuscation or deceptive metadata was detected.
- [SAFE]: The skill properly handles authorization by directing the client to use established MCP transport mechanisms (API keys or OAuth) rather than hardcoding credentials or using unsafe local storage.
Audit Metadata