modal-compute
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
modalCLI and uses thetorchlibrary within its remote image definition. Both are well-known, legitimate packages from official registries used according to their intended purpose. - [COMMAND_EXECUTION]: The skill facilitates the execution of scripts and interactive shells via the
modalCLI. These commands are necessary for the skill's primary function of running burst compute jobs on remote infrastructure. - [INDIRECT_PROMPT_INJECTION]: The skill functions by executing agent-generated Python code on a serverless platform. While this processes external instructions, it represents the primary, documented capability of the skill and incorporates standard image-based isolation provided by the compute vendor.
Audit Metadata