add-tools
Add tools to your agent and grant required permissions in databricks.yml. Use when: (1) Adding MCP servers, Genie spaces, vector search, or UC functions to agent, (2) Permission errors at runtime, (3) User says 'add tool', 'connect to', 'grant permission', (4) Configuring databricks.yml resources.
65
77%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./agent-langgraph-advanced/.claude/skills/add-tools/SKILL.mdLow
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
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
The runtime workflow only loads MCP tool definitions by calling `mcp_client.get_tools()` from configured Databricks MCP endpoints (via `url=.../api/2.0/mcp/...`) and does not describe ingesting arbitrary outsider-authored free text without selecting a specific tool/resource.
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
The skill constructs and calls MCP server endpoints at runtime (e.g., f"{host}/api/2.0/mcp/genie/01234567-89ab-cdef" and https://mcp-my-server.cloud.databricks.com/mcp) and then calls mcp_client.get_tools(), meaning remote content from those URLs is fetched during runtime and provides the agent's tool definitions/instructions that directly control prompts.
- Repository
- databricks/app-templates
- Commit
fdc1b49
- 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.