setup-python-env
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill manages Python environments exclusively through the 'skore_skills' CLI tool, which is a resource provided by the author ('probabl-ai'). The instructions contain an explicit security control forbidding the use of unsafe remote execution patterns like 'curl | sh'.
- [COMMAND_EXECUTION]: The skill performs shell execution of 'skore_skills' commands to initialize environments, synchronize packages, and verify the setup. These operations are limited to the specific capabilities of the environment manager tool.
- [INDIRECT_PROMPT_INJECTION]: The skill features a potential attack surface by interpreting external data to drive its internal logic, though the risk is minimized by the skill's specific purpose.
- Ingestion points: The skill processes output from 'python -m skore_skills env detect' and reads local configuration files such as 'pixi.toml'.
- Boundary markers: No explicit delimiters are used in the instructions to separate tool output from instructions.
- Capability inventory: The skill can execute environment initialization, synchronization, and package addition through the 'skore_skills' tool.
- Sanitization: Input validation and sanitization are delegated to the underlying 'skore_skills' CLI tool rather than being handled within the skill instructions.
Audit Metadata