dbt-labs/dbt-agent-skills
A curated collection of Agent Skills for working with dbt, to help AI agents understand and execute dbt workflows more effectively.
65
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Passed
Use when adding unit tests for a dbt model or practicing test-driven development (TDD) in dbt
Passed
Use when a user asks a business question that requires querying data (e.g., "What were total sales last quarter?"). NOT for validating, testing, or building dbt models during development.
Passed
Use when creating or modifying dbt Semantic Layer components — semantic models, metrics, dimensions, entities, measures, or time spines. Covers MetricFlow configuration, metric types (simple, derived, cumulative, ratio, conversion), and validation for both latest and legacy YAML specs.
Risky
Use when setting up, configuring, or troubleshooting the dbt MCP server for AI tools like Claude Desktop, Claude Code, Cursor, or VS Code.
Passed
Use when fetching dbt documentation, looking up dbt features, or answering questions about dbt Cloud, dbt Core, or the dbt Semantic Layer
Advisory
Guides migration of dbt projects from dbt Core to the Fusion engine. Use when making a project compatible with Fusion, addressing deprecations, or running dbtf commands.
Passed
Use when executing dbt commands via CLI - running models, tests, builds, compiles, or show queries. Use when unsure which dbt executable to use or how to format command parameters.
Advisory
Use when a dbt Cloud/platform job fails and you need to diagnose the root cause, especially when error messages are unclear or when intermittent failures occur. Do not use for local dbt development errors.
Advisory
Use when doing any dbt work - building or modifying models, debugging errors, exploring unfamiliar data sources, writing tests, or evaluating impact of changes. Use for analytics pipelines, data transformations, and data modeling.
Security
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.md explicitly directs the agent to consult and use external public resources (e.g., https://docs.getdbt.com, the dbt-autofix GitHub link, the dbt-fusion GitHub discussion, and public.cdn.getdbt.com schema URLs) as required resources for resolving migration issues, so the agent would fetch and interpret untrusted, user-visible third-party web content that could influence 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 workflow explicitly requires installing and running dbt-autofix (https://github.com/dbt-labs/dbt-autofix) during runtime, which will fetch and execute remote code and is relied on as a required dependency for the migration steps.
- Audited
- Security analysis