outlook

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill stores client secrets and OAuth tokens in ~/.outlook-mcp and explicitly exposes a ./scripts/outlook-token.sh get command that prints the access token, meaning the agent would need to access and could output secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.90). This skill fetches and reads user-generated, untrusted email and calendar content directly from Microsoft Graph (e.g., scripts/outlook-mail.sh calling https://graph.microsoft.com/v1.0/me/messages and scripts/outlook-calendar.sh calling https://graph.microsoft.com/v1.0/me/calendar/events), and those contents are returned and used by the agent (read/display and could drive replies/creates), enabling indirect prompt-injection risk.