agent-email

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow for this agent skill manages email through CLI tools (mail-cli and agently-cli), monitoring, reading, searching, and processing incoming emails from external senders, which exposes the agent to outsider-authored free text via email bodies, subjects, sender names, and attachments.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The script fetches credential resolution content from an external redirect domain (u.163.com) via curl -sL during setup, representing an unverifiable runtime external dependency under weak/unknown provenance.