red-teaming-llms-with-garak

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow invokes garak with a user-supplied --target_type rest and -G rest.json (arbitrary uri), so the LLM ingests outsider-authored free text from the remote REST endpoint’s response (extracted via response_json_field) into the agent’s .report.jsonl/summarization context.