better-interface
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill identifies and executes existing project-specific "preview or test commands" to verify the UI state. This capability is used to confirm visual or functional findings within the development environment.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code and interface components from the project workspace.
- Ingestion points: Source files, components, and rendered UI states (File: SKILL.md).
- Boundary markers: The instructions do not specify delimiters or guidelines to ignore instructions embedded in the analyzed code.
- Capability inventory: Includes file system read access and execution of project-defined shell commands.
- Sanitization: No explicit filtering or escaping of ingested source content is mentioned.
Audit Metadata