databricks-agent-bricks
Create and manage Databricks Agent Bricks: Knowledge Assistants (KA) for document Q&A, Genie Spaces for SQL exploration, and Supervisor Agents (MAS) for multi-agent orchestration. Use when building conversational AI applications on Databricks.
83
78%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./databricks-skills/databricks-agent-bricks/SKILL.mdSecurity
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
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
Third-party content exposure detected (high risk: 0.80). The skill's "External MCP Servers" workflow (2-supervisor-agents.md) configures Unity Catalog HTTP Connections to external JSON-RPC MCP endpoints that the Supervisor Agent will call and read tool descriptions/schemas from, meaning the agent ingests untrusted external server content that can drive routing and actions.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.80). The skill documents using an external MCP JSON-RPC endpoint via a Unity Catalog HTTP Connection (e.g., https://my-app.databricksapps.com/api/mcp) that is called at runtime (tools/list, tools/call) to provide tool definitions and perform actions, so that external URL can directly influence agent behavior and execute remote operations.
- Repository
- databricks-solutions/ai-dev-kit
- Commit
b4071a0
- 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.