pint-compute
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill performs computations by invoking a local script,
scripts/pint_compute.py, using theuvtool. This is a standard execution flow for providing additional computation capabilities to an agent.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes unit strings provided as input. While this constitutes an external data ingestion surface, the specific context of unit arithmetic and the use of a specialized parsing script minimizes the risk of indirect instruction execution.
Audit Metadata