azure-upgrade

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

• Third-party content exposure detected (high risk: 1.00). The skill's automation steps explicitly instruct fetching and downloading remote deployment packages and hitting function app URLs (see references/services/functions/automation.md Step 3f and Post-Upgrade Validation), which requires the agent to fetch and act on arbitrary external/user-hosted content that can materially change behavior.