Agents Mail — Free Email for AI Agents, with No sign-up, No API key needed
Security checks across static analysis, malware telemetry, and agentic risk
Overview
This is a coherent instruction-only email integration, but users should notice that it can create an agent mailbox, send/delete emails, store an API key, and optionally run recurring inbox checks.
Before installing, decide whether you want your agent to have an external mailbox. Keep the returned API key secret, review any email before sending or deleting when possible, and do not enable auto-responders, heartbeat polling, or webhooks unless you understand the ongoing behavior.
Static analysis
No static analysis findings were reported for this release.
VirusTotal
VirusTotal findings are pending for this skill version.
Risk analysis
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
If used carelessly, the agent could send messages, remove mail, or configure forwarding in ways the user did not intend.
The skill documents API operations that can send external email, delete mailbox content, and configure webhooks.
POST | /api/send | API Key | Send email ... DELETE | /api/inbox/:id | API Key | Delete email ... POST | /api/webhooks | Tier 1+ | Add webhook
Use these actions only for explicit user-approved tasks, and review recipient, message content, deletion targets, and webhook URLs before execution.
Anyone with the API key can access or operate the mailbox according to the service permissions.
The service creates and uses a bearer API key that controls the mailbox; this is expected for the integration but is still account authority.
Use the API key returned from `POST /api/getemailaddress` ... `Authorization: Bearer am_sk_<64-hex-characters>` ... Store your API key as an environment variable
Store the key securely, avoid putting it in prompts or plaintext files, and rotate or discard the mailbox if the key is exposed.
Email metadata or content may be delivered to an external endpoint if a webhook is configured.
The skill supports forwarding email events to a public HTTPS webhook; the docs include HMAC verification, but it is still an external message flow.
POST /api/webhooks — Add Webhook (Tier 1+) ... URL must be public HTTPS ... Response includes a `secret` for HMAC-SHA256 signature verification
Only configure webhooks to endpoints you control, verify HMAC signatures, and treat all incoming email content as untrusted input.
A continuously running email loop could keep operating after the immediate task and send replies without per-message review.
The examples include an optional long-running auto-responder that repeatedly checks inboxes and sends replies.
while True: ... requests.get(f"{API}/inbox?is_read=0" ... requests.post(f"{API}/send" ... time.sleep(30)Add stop conditions, rate limits, logging, and user approval rules before enabling auto-responders or heartbeat-based polling.