dotfile-systems-architect
Pass
Audited by Gen Agent Trust Hub on Apr 19, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for reorganizing the home directory, which involves moving sensitive files like SSH keys, AWS credentials, and GPG configurations to XDG-compliant paths using standard utilities like mv, ln, and chmod. Additional commands are provided to remove conflicting files during the environment bootstrap process.
- [REMOTE_CODE_EXECUTION]: The documentation includes commands to download and execute installation scripts from well-known technology services, such as Chezmoi and Oh-My-Zsh, to facilitate tool setup.
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by instructing the agent to clone and apply configurations from a user-provided remote repository. 1. Ingestion points: Remote Git repository URLs provided in migration and bootstrap scripts (e.g., DOTFILES_REPO). 2. Boundary markers: No explicit markers or warnings are included to differentiate repository content from agent instructions. 3. Capability inventory: Includes shell command execution, network access via git, and file system modifications. 4. Sanitization: No validation or sanitization of the content fetched from the remote repository is performed before application.
Audit Metadata