graphql-inspector-diff

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly supports fetching schemas from arbitrary remote URLs (see "URL-Based Comparison" examples like 'https://api.example.com/graphql' and the "Schema Sources" entry with old: url: https://api.example.com/graphql), so the agent will ingest and interpret untrusted third-party content as part of its workflow.