testing-api-tester

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow explicitly instructs the agent to "catalog all internal and external APIs" and the provided test suite examples call fetch(${baseURL}/...) to ingest and evaluate API responses from external/third-party endpoints, so the agent will read and act on untrusted third-party API content that can influence its decisions.