abai-autoplus-chatgpt-registration

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads incoming emails via IMAP to retrieve verification codes during account registration, exposing the agent to outsider-authored free text in incoming emails.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill includes a git clone installation instruction referencing a personal third-party GitHub repository (https://github.com/asz798838958/freeAgentIdentity.git), which constitutes an external runtime/setup dependency with unofficial provenance.