databricks-genie

Warn

Audited by Snyk on Apr 9, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill's migration workflow (spaces.md "Export, Import & Migration" and the agent workflow steps) requires exporting a serialized_space via migrate_genie(type="export"), reading and modifying that user-generated serialized_space (the .replace remapping example), and importing it back; the serialized_space contains instructions, example_question_sqls, SQL snippets and join specs that the agent consumes and which can directly change behavior, so it exposes the agent to untrusted third-party content.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 9, 2026, 10:55 AM
Issues
1