wpf-mvvm-generator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs standard code generation tasks for WPF MVVM applications.
- [INDIRECT_PROMPT_INJECTION]: The skill reads existing project files to extract namespaces and coding patterns, creating an indirect prompt injection surface. Ingestion points: Files matching
Glob("**/*ViewModel.cs")and those read via theReadtool (SKILL.md). Boundary markers: None identified. Capability inventory:Write,Edit,Read,Glob(SKILL.md). Sanitization: None identified. The risk is limited as the skill lacks network access or high-privilege execution capabilities. - [COMMAND_EXECUTION]: No unauthorized command execution patterns were found. The skill uses allowed tools for file system interaction (Read, Glob, Write, Edit) which are appropriate for its stated purpose of scaffolding code.
- [DATA_EXFILTRATION]: No network tools are requested or used. The skill does not access sensitive system files (e.g., .ssh, .aws) or hardcoded credentials.
Audit Metadata