modify-agent
Modify agent code, add tools, or change configuration. Use when: (1) User says 'modify agent', 'add tool', 'change model', or 'edit agent.py', (2) Adding MCP servers to agent, (3) Changing agent instructions, (4) Understanding SDK patterns.
68
81%
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
Low
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 skill shows creating/adding MCP servers (e.g., DatabricksMCPServer.from_vector_search and a Non-Databricks MCPServer with url="https://other-server.com/mcp") and calling client.get_tools() to fetch tool definitions that are then passed into create_agent(tools=tools), which means arbitrary external/untrusted MCP-hosted content is ingested and can directly influence agent 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
The skill explicitly fetches MCP tool definitions at runtime from external MCP endpoints (e.g., "{host}/api/2.0/mcp/functions/system/ai" and the example "https://other-server.com/mcp") via DatabricksMultiServerMCPClient.get_tools(), which can supply tool behaviors that alter agent actions and execute remote code, so this is a runtime external dependency that can control the agent.
- 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.