flutter-mcp-toolkit-inspect
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected in the skill instructions or tool definitions.
- [COMMAND_EXECUTION]: The skill interacts with the local Flutter VM Service via WebSocket connections (127.0.0.1) to retrieve application state. This is standard behavior for debugging and inspection tools.
- [DATA_EXFILTRATION]: No exfiltration patterns were found. The skill retrieves screenshots, error logs, and widget trees from a local process and returns them to the agent context or saves them to a locally configured directory.
- [PROMPT_INJECTION]: The instructions are focused on tool usage and do not contain attempts to override safety guidelines or agent behavior.
- [EXTERNAL_DOWNLOADS]: The skill does not perform external downloads or reference untrusted remote resources.
Audit Metadata