workspace-os-setup
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFE
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill utilizes bundled scaffolding scripts (
scaffold-workspace-os.shandscaffold-workspace-os.ps1) to initialize the workspace environment. These scripts perform local directory creation and text substitution within template files. It also includes instructions to optionally install the 'skill-creator' tool from a trusted repository, with an explicit requirement for the agent to seek user permission before execution. - [COMMAND_EXECUTION]: The setup workflow directs the agent to execute specific shell or PowerShell commands to run the local scaffolding scripts. These scripts include robust safety checks to prevent data loss, such as verifying the target directory is not a broad system folder and ensuring it does not already contain an existing Workspace OS configuration.
- [PROMPT_INJECTION]: The skill is architected to process external data like meeting notes and project documents. It mitigates indirect prompt injection risks by instructing the agent to isolate raw inputs into
raw/folders and providing clear structural boundaries between agent-facing machinery and user-provided content. - [SAFE]: All external URLs and package references trace back to the author's verified infrastructure or well-known trusted vendors. No malicious behavior, such as credential harvesting, obfuscation, or unauthorized network communication, was detected.
Audit Metadata