ui-uitk
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests existing project files to perform edits and generation, which creates a potential surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: Processes existing UXML, USS, and C# files from the project workspace during the editing and generation workflows (SKILL.md, Editing/Generation sections).
- Boundary markers: There are no explicit instructions to use boundary markers or to ignore embedded instructions within the files being processed.
- Capability inventory: The skill has the capability to write and modify files in the project and generate C# code for UI logic (SKILL.md, Generation workflow).
- Sanitization: The instructions do not define sanitization or validation steps for content extracted from existing project files before it is processed by the agent.
Audit Metadata