legal-research-assistant

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs the agent to fetch and parse content from open public legal websites—notably Indian Kanoon (indiankanoon.org), India Code (indiacode.nic.in), e-Courts and various third-party legal blogs—which are external, publicly editable/aggregated sources the agent will read as part of its workflow, exposing it to untrusted third‑party content and potential indirect prompt injection.