remote-compute-modal

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for using the Modal CLI to verify credentials and submit remote compute jobs, which is the intended and legitimate purpose of the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes research notebooks and experiment scripts which could contain external instructions. It mitigates this risk by requiring bounded inputs, explicit package installs, and artifact monitoring.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 01:47 AM
Security Audit — agent-trust-hub — remote-compute-modal