powerskills-outlook

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

• Third-party content exposure detected (high risk: 0.80). The skill directly reads and returns email bodies and items from the user's Outlook mailbox (see SKILL.md and outlook.ps1 actions like inbox/unread/read/search and reply/send), which are untrusted user-generated third-party content that could contain instructions influencing replies or other actions.