Add Trustabl security scanning to CI

[joshua-trustabl]

We came across your repo and we like how you're building a reactive multi-agent system to orchestrate scientific computing workflows, blending the power of physics-informed neural networks with MLflow for tracking and provenance. We scanned the repo, and noticed agent runtime reliability findings that might be worth reviewing.

1. [CRITICAL] Bundled skill script reads credentials or secrets
   File: .claude/Skills/mlflow/SKILL.md
   What it means: A script bundled with this skill reads credentials or secrets (gh auth, $AWS_*, ~/.
2. [MEDIUM] LlmAgent description missing
   File: .claude/agents/LLM_AGENT.yaml
   What it means: The LLM Agent description is missing, making it difficult to understand its purpose and capabilities.

Recommendations are based on our understanding of agent runtime reliability, some findings may be intentional. Please let us know if this was intentional or if our findings are helpful so we can improve the accuracy of the scanner.

Best,
Trustabl.ai
Open-source AI agent reliability scanner (runs locally, GitHub Action)