dspy-mlflow
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the mlflow library from the official Python package index.
- [COMMAND_EXECUTION]: Instructions include running the mlflow ui command to launch a local dashboard for viewing traces and experiment metrics.
- [PROMPT_INJECTION]: The skill processes untrusted data through a RAG pipeline, representing a surface for indirect prompt injection.
- Ingestion points: question parameter in SupportQA.forward and data in trainset.
- Boundary markers: Not present.
- Capability inventory: The skill does not possess high-risk capabilities such as arbitrary subprocess execution or file system writes outside of logging.
- Sanitization: No explicit validation or filtering of input data is included in the examples.
Audit Metadata