breach-data

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

• Third-party content exposure detected (high risk: 0.90). The skill directly queries public breach and paste services (e.g., HaveIBeenPwned API at https://haveibeenpwned.com/api/v3, Pastebin URLs via pasteaccount, and third‑party APIs like DeHashed and IntelX) and ingests and interprets their responses in functions such as check_email, check_pastes, check_dehashed, and check_intelx to drive reporting and decisions, exposing the agent to untrusted user-generated content.