databricks-repl-consolidate
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions define a clear and limited workflow for reading local
.jsonand.pyfiles within the Databricks environment and reformatting their content into a single output file. - [SAFE]: No external network requests, sensitive file access (e.g., SSH keys, credentials), or obfuscated code patterns were detected.
- [SAFE]: The transformation rules (stripping
%pip installand removing REPL-specific print statements) are standard code-cleaning operations and do not involve executing the untrusted content. - [PROMPT_INJECTION]: While the skill processes user-generated command files (
.cmd.py), which represents a potential indirect prompt injection surface, the instructions are specific and rigid, focusing on structural consolidation rather than using the file content to influence agent logic. This is considered a low-risk, standard operational characteristic for code-processing skills.
Audit Metadata