wizard
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [SAFE]: The skill implements legitimate developer workflows for secret management and environment configuration without any detected malicious patterns.
- [COMMAND_EXECUTION]: The generated scripts use local commands such as
gh(GitHub CLI) to manage secrets and system utilities (xdg-open,open, etc.) to facilitate browser-based setup steps. - [INDIRECT_PROMPT_INJECTION]: The skill analyzes local repository files (e.g.,
.env.example,README) to determine setup requirements. This ingestion point is a potential surface for indirect injection if repository files are malicious, though the resulting script is intended for human execution and review. - [DYNAMIC_EXECUTION]: The skill generates shell scripts based on a predefined local template (
template.sh). This represents standard template-based code generation.
Audit Metadata