self-determined-project-design-protocol

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

• Third-party content exposure detected (high risk: 0.70). The skill’s runtime prompt includes user-provided free text fields (e.g., {{student_idea}}), which are outsider-authored if the operating user did not author them; this text is directly injected into the LLM context via the “Your task is to design…” prompt template.