dbt-migration

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to search and fetch GitHub issues (e.g., "search site:github.com/dbt-labs/dbt-fusion/issues" and the allowed-tool WebFetch(domain:api.github.com)), which are public, user-generated pages that the agent is required to read and use to decide classification and next actions, so untrusted third-party content could inject instructions indirectly.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly requires running dbt-autofix at runtime using the command "uvx --from git+https://github.com/dbt-labs/dbt-autofix.git dbt-autofix deprecations", which fetches and executes code from that Git repository and is a required dependency, so it is a runtime external dependency that can execute remote code.