nextjs-create-regression-test
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- Standard Command Execution: The skill involves running test commands, linters, and formatting tools (e.g., Workflow steps 5 and 8). This is standard behavior for development-oriented tasks within a local repository environment.
- Indirect Prompt Injection Surface: The skill processes external data sources including issue descriptions and web pages. It proactively addresses this by instructing the agent to treat issue text, repository content, and tool output as untrusted data (Boundaries section), which is a recommended security practice to prevent unauthorized instruction execution.
- Controlled File System Operations: The skill is designed to add specific test files without modifying existing product code. It maintains high oversight by requiring explicit user confirmation before committing or pushing changes.
Audit Metadata