hunt-html-injection

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

• Third-party content exposure detected (low risk: 0.10). The required workflow sends test payloads to a user-specified target application and then fetches the pages where they render (line 49), so outsider-authored text such as other users' comments or profile fields is read only after the agent selects a specific page, which makes this low risk.