Skills
skills/a5c-ai/babysitter/wpf-mvvm-scaffold/Gen Agent Trust Hub

wpf-mvvm-scaffold

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through the ingestion of user-provided strings such as projectName and generateViewModels. These inputs are used to generate file paths and content, which is a standard feature for a scaffolding tool.\n
  • Ingestion points: Input parameters projectName and generateViewModels defined in the SKILL.md schema.\n
  • Boundary markers: No explicit boundary markers are present in the provided templates to delimit untrusted input.\n
  • Capability inventory: The skill has access to Write, Edit, and Bash tools to modify the local file system.\n
  • Sanitization: No sanitization is performed on the input strings prior to file generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 04:12 AM