Skills
skills/arenukvern/mcp_flutter/flutter-mcp-toolkit-dogfood-iterations/Gen Agent Trust Hub

flutter-mcp-toolkit-dogfood-iterations

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute several local commands including bash, make, and dart. These are used to run evaluation scripts (tool/evals/run_dogfood_eval.sh), trigger Makefile targets (make web-showcase), and execute Dart tools (flutter_mcp_toolkit.dart). These operations are consistent with the skill's purpose as a development and testing utility.
  • [DATA_EXPOSURE]: The skill parses a local log file (.showcase/web_app.log) to extract a WebSocket URI for a local VM service. The extraction logic uses a restrictive regex that targets 127.0.0.1, ensuring the connection remains local to the development environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 04:41 PM
Security Audit — agent-trust-hub — flutter-mcp-toolkit-dogfood-iterations