databricks-mlflow-evaluation
MLflow 3 GenAI agent evaluation. Use when writing mlflow.genai.evaluate() code, creating @scorer functions, using built-in scorers (Guidelines, Correctness, Safety, RetrievalGroundedness), building eval datasets from traces, setting up trace ingestion and production monitoring, aligning judges with MemAlign from domain expert feedback, or running optimize_prompts() with GEPA for automated prompt improvement.
70
86%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
This skill explicitly ingests user-generated production traces (e.g., via mlflow.search_traces and eval_dataset.merge_records in patterns-datasets.md / patterns-evaluation.md / patterns-judge-alignment.md) and then reads and uses those trace contents in evaluate(), judge alignment (align()), and optimize_prompts(), so untrusted third-party inputs are consumed and can materially influence scoring and downstream actions.
- Repository
- databricks-solutions/ai-dev-kit
- Commit
a7e1d51
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.