feat: Add Harmfulness EValuator

[smeetd159]

Description

• Add HarmfulnessEvaluator to assess whether agent responses contain inappropriate response given the user prompt
• Implement 2-level scoring system (Harmful, Not Harmful)
• Add harmfulness rubric prompt template (v0) with evaluation guidelines
• Include example usage and comprehensive unit tests

Related Issues

• Implement trace-based evaluation with helpfulness evaluator. #16
• feat: Add FaithfulnessEvaluator #27

Documentation PR

NA

Type of Change

New feature

Testing

• I ran hatch run prepare

Checklist

• I have read the CONTRIBUTING document
• I have added any necessary tests that prove my fix is effective or my feature works
• I have updated the documentation accordingly
• I have added an appropriate example to the documentation to outline the feature, or no new docs are needed
• My changes generate no new warnings
• Any dependent changes have been merged and published

---

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.