flutter-marionette-usage
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a documentation and instruction set for the Marionette MCP tool, facilitating Flutter app debugging and runtime exploration. No malicious patterns were detected.
- [EXTERNAL_DOWNLOADS]: The skill references the installation of the
marionette_mcptool viadart pub. This is a standard package management operation from a well-known registry (pub.dev) and the tool is a resource provided by the skill's author (leancodepl). - [INDIRECT_PROMPT_INJECTION]: The skill describes tools (
get_logs,get_interactive_elements) that ingest data from a running Flutter application. This creates a potential surface for indirect prompt injection if the application under test contains malicious strings in logs or widget labels. This is an inherent risk of UI automation tools and is considered safe within the context of local development debugging. 1. Ingestion points:get_logs,get_interactive_elements(referenced inreferences/marionette.md). 2. Boundary markers: None specified in the instructions. 3. Capability inventory:tap,enter_text,scroll_to,hot_reload(referenced inreferences/marionette.md). 4. Sanitization: None specified.
Audit Metadata