agent-mail

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow reads incoming email messages via AgentMail, which allows unauthenticated outsiders to submit free text directly into an inbox monitored by the agent.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs execution of npx @useclawlink/cli, which downloads and executes packages from npm without an explicit repository locator or strong first-party enterprise provenance, meeting the criteria for a weak runtime external dependency.