trunative-flutter
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable code in the form of scripts; it consists of markdown-based instructions and JSON configuration files.
- [SAFE]: The skill references standard development tools and command-line interfaces such as adb-agent, npx, and xcrun. These are used appropriately for the stated purpose of mobile app UI review and testing.
- [SAFE]: The skill incorporates robust privacy and security guidelines that explicitly aim to prevent data exposure and follow platform security standards.
- [INDIRECT_PROMPT_INJECTION]: The skill has an inherent attack surface for indirect prompt injection because its workflow involves the AI agent ingesting and analyzing external project files, code, and UI metadata. This exposure is fundamental to the skill's purpose as a design and code reviewer.
- [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands to interact with connected mobile devices to perform tasks like changing font scales or taking screenshots. These actions are strictly within the scope of mobile UI testing.
Audit Metadata