python-django

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

• Third-party content exposure detected (high risk: 0.95). The required workflow explicitly performs runtime web-search and fetches external documentation pages (e.g., Django ORM/signals, Celery user guide, Saleor developer docs, Python typing docs), which are outsider-authored free text ingested into the agent’s LLM context via the “Fetch live docs” steps.