performing-graphql-security-assessment

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

• Third-party content exposure detected (high risk: 0.80). The skill actively sends requests to arbitrary GraphQL endpoints (see scripts/agent.py _query posting to the provided target_url and SKILL.md curl examples to https://target.example.com/graphql) and parses untrusted JSON responses (schema, errors, suggestions) which are used to determine vulnerabilities and next actions, so third-party content can materially influence behavior.