atlan-cli-run-test-loop
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes various system commands to verify environment state and run applications, including
atlan,uv,dapr, andtemporal. - [EXTERNAL_DOWNLOADS]: The skill triggers the installation of the
atlanCLI via a secondary skill (atlan-cli-install-configure) if the binary is missing from the system path. This represents a download of a vendor-provided tool from an established ecosystem. - [PROMPT_INJECTION]: The skill processes and executes code from a user-provided application path through commands like
uv run main.pyandpytest. This represents a surface for indirect injection if the source code originates from an untrusted source. - Ingestion points: Target application directory contents at
<app_path>. - Boundary markers: None identified.
- Capability inventory: Subprocess execution of Python code, shell commands, and test suites.
- Sanitization: The skill does not sanitize or validate the application source code before execution.
Audit Metadata