python-cola-skill

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text from the operating user’s HTTP request is ingested via adapter/routes/user_routes.py using request.get_json() / request.args.get(...), then placed into DTO fields (UserCO, UserListQry) and passed through the application/service into the LLM context if the agent later summarizes/uses these values.