databricks-docs

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch a documentation index from the official Databricks domain (docs.databricks.com). This is a standard vendor resource provided for reference purposes.
  • [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by design, as it requires reading and processing external documentation content from a remote URL. This is necessary for the skill's primary function as a documentation reference.
  • Ingestion points: External content is retrieved from https://docs.databricks.com/llms.txt using the agent's WebFetch capabilities.
  • Boundary markers: The instructions do not define specific delimiters or boundary markers for the retrieved content.
  • Capability inventory: The skill itself does not contain scripts or direct command execution but is intended to inform the use of other MCP tools (e.g., execute_sql).
  • Sanitization: There are no explicit sanitization steps defined within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 10:55 AM