saleor-testing

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to fetch and review live public documentation and code (e.g., web-searching docs.saleor.io, docs.pytest.org, and fetching https://github.com/saleor/saleor/blob/main/conftest.py) so the agent will read untrusted, user-controlled third-party content that can influence its actions.