secondme

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

• Third-party content exposure detected (medium risk: 0.30). The agent skill required workflow includes a chat endpoint (references/chat.md) and report ingestion (references/avatar.md) that handle arbitrary messages and report pages which can contain outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill contains an explicit runtime installation command (npx skills add https://second-me.cn) that fetches and executes code from an unverified third-party domain under user invocation, constituting a weak/unknown external operational dependency.