openjung-api

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

• Third-party content exposure detected (high risk: 0.70). This skill explicitly fetches and ingests live content from the public openjung.org API (see SKILL.md Quick Start fetch('https://openjung.org/api/questions') and the GET /api/questions endpoint in references/api_reference.md), so the agent reads and acts on third-party website data (questions and typeInfo) that could plausibly contain injected instructions affecting its outputs or actions.