GraphQL Schema Introspection Analyzer

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly performs GraphQL introspection by sending the standard __schema query to arbitrary GraphQL APIs (see SKILL.md), ingesting and analyzing third-party schema content that can materially influence analysis and agent outputs and thus could carry indirect prompt-injection content.