cw-setup-project
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a bundled Python script (
create_project.py) viapython3to perform directory and file creation. This script uses standard library functions to copy templates from a predefined location within the plugin structure to a user-specified target path. - [INDIRECT_PROMPT_INJECTION]: The skill's migration logic involves reading and interpreting instructions from a user-provided file (
TASTE.md), which represents a potential injection surface. - Ingestion points: The agent reads existing workspace instructions and the
TASTE.mdfile during the migration workflow described inSKILL.md. - Boundary markers: No specific boundary markers or "ignore instructions" warnings are defined for the content read from the legacy project files.
- Capability inventory: The skill possesses the capability to execute shell commands (to run the setup script) and perform file system operations (creating folders and copying files).
- Sanitization: The instructions do not specify any sanitization, filtering, or validation of the content processed from
TASTE.mdbefore it is used to guide the migration and project setup.
Audit Metadata