Mails for Agent

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly requires making HTTP requests with the header "Authorization: Bearer $MAILS_AUTH_TOKEN" (and using $MAILS_API_URL/$MAILS_MAILBOX), which forces the agent to insert secret token/mailbox values verbatim into requests and outputs, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime flow can ingest outsider-authored free text from the mailbox via GET /api/email?id=ID (email body/headers/metadata) and potentially from real-time GET /api/events SSE messages, which are not authored by the operating user.