netbox-review-datamodel

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow can ingest outsider-authored free text via “Data model docs” URLs (public web pages fetched at runtime) and/or via an optional NetBox MCP server that returns instance data (which may include user-entered descriptions/comments), both of which can be read as prose and placed into the agent’s LLM context.