Enables sending outbound emails via AgentMail.to for system alerts and task completion reports using [email protected].

Do not install or enable this skill until the author fixes the mismatches. Ask the publisher to: (1) declare the exact environment variable name(s) for the AgentMail API key in the skill metadata, (2) include the send_mail.py source (or a trusted install specification) so you can review its behavior, and (3) explain exactly what system data the skill will read (e.g., temperature sensors, logs) and how credentials will be stored. If you must use it before those clarifications, limit the agent's ability to run autonomously and do not provide high-privilege or long-lived credentials—prefer a dedicated, scoped API key that can be revoked quickly. Verify AgentMail.to is a legitimate service and that sending from [email protected] is authorized.

Type: OpenClaw Skill Name: agent-email Version: 1.0.0 The skill bundle contains metadata and documentation for an outbound email notification service via the AgentMail.to API. The SKILL.md and skill.yaml files describe standard alerting and reporting functionality (e.g., system health, task completion) without any evidence of malicious intent, prompt injection, or suspicious exfiltration logic. While the implementation script (send_mail.py) is referenced but not included in the provided files, the documentation itself is consistent with its stated purpose.