GraphQL Schema Introspection Mapper

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly states the skill "introspects GraphQL APIs via the __schema query", so it fetches and parses schemas from arbitrary GraphQL endpoints (third-party/public APIs) which the agent uses to drive code-generation and analysis, allowing untrusted schema content to influence subsequent actions.