setup-project
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads project templates from the author's GitHub repository (
gh:RobertDeRose/dstack). It also orchestrates the download and installation of various standard developer tools via themisemanager, includinguv,mdbook,ruff, andhk(v1.49.0). - [COMMAND_EXECUTION]: The skill executes shell commands for Git repository initialization,
misetool management, andbd(Beads) workflow initialization. These operations are performed usingsubprocess.runwith structured argument lists, mitigating command injection risks. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data (such as project purpose, scope, and boundaries) collected via
AskUserQuestionand interpolates them into Markdown documentation templates (AGENTS.md,README.md). - Ingestion points: User input from
AskUserQuestioninSKILL.md. - Boundary markers: Templates use explicit
<!-- BEGIN DSTACK WORKFLOW -->comments to delimit generated content. - Capability inventory: Writing to the filesystem and executing shell commands (Git, mise).
- Sanitization: The skill employs a Jinja2 macro (
markdown) in template files to escape Markdown special characters (e.g.,#,*,[,],`), preventing user-provided text from breaking the documentation structure or injecting malicious Markdown instructions.
Audit Metadata