@inboxapi/cli 0.2.8 → 0.2.10

package/README.md

@@ -7,7 +7,7 @@ Give your AI agent its own email address. Send, receive, read, search, and reply
 Copy and paste this sentence into your agent:  
 
 ```
-Install the `@inboxapi/cli` npm package globally and then register the `inboxapi` command as an MCP server named `inboxapi`.
+Install the `@inboxapi/cli@latest` npm package globally and then register the `inboxapi` command as an MCP server named `inboxapi`.
 ```
 
 <details>
@@ -48,14 +48,14 @@ The CLI acts as a local bridge between your AI client and the [InboxAPI](https:/
 
 - **This is your agent's personal email** — InboxAPI gives your AI agent its own email address for personal use. It is not a transactional email service — don't use it for bulk sending, marketing, or application notifications.
 - **Weekly send limit** — Each account can send to up to five unique email addresses per week. This resets weekly.
-- **Check your spam folder** — Emails from InboxAPI may land in your junk or spam folder. If you're not seeing messages, check there first.
+- **Check your spam folder** — Each agent gets its own subdomain, and new subdomains don't have email reputation yet. Early messages may land in your recipient's spam or junk folder. Adding your agent's email address to your contacts or allowlist helps. Delivery improves over time as recipients interact with your agent's emails.
 - **No attachments yet** — Attachment support is not available right now, but it's coming soon.
 - **No rich text yet** — Emails are sent as plain text only. Rich text (HTML) support is coming soon.
 
 ## Installation
 
 ```bash
-npm install -g @inboxapi/cli
+npm install -g @inboxapi/cli@latest
 ```
 
 Prebuilt binaries are included for:
@@ -66,6 +66,16 @@ Prebuilt binaries are included for:
 | Linux          | x64, ARM64   |
 | Windows        | x64          |
 
+## Updating
+
+Run the same install command to update to the latest version:
+
+```bash
+npm install -g @inboxapi/cli@latest
+```
+
+The CLI also checks for updates automatically when running in proxy mode and installs them in the background.
+
 ## Getting Started
 
 Just start the proxy — an account is created automatically on first run
@@ -183,22 +193,22 @@ gemini mcp add inboxapi inboxapi --scope user
 
 **OpenCode:**
 
-Add to current project:
+Run the interactive setup:
 
 ```bash
-opencode mcp add inboxapi inboxapi
+opencode mcp add
 ```
 
-Add globally (available in all projects):
-
-```bash
-opencode mcp add inboxapi inboxapi -s user
-```
+When prompted, enter:
+- **Location:** Global
+- **MCP server name:** inboxapi
+- **MCP server type:** Local
+- **Command to run:** inboxapi
 
 **Codex CLI:**
 
 ```bash
-codex mcp add inboxapi -- inboxapi
+codex mcp add inboxapi inboxapi
 ```
 
 ## Development
@@ -226,15 +236,21 @@ Yes. No credit card, no trial period, no usage tiers. We're working on paid plan
 
 **How do you prevent spam and abuse?**
 
-Account creation requires proof-of-work. Each account can only email 5 unique external domains per week. Daily send quotas and rate limiting are enforced on every account. These constraints are structural — they're not policies, they're how the system works.
+Account creation requires proof-of-work. Each account can only email 5 unique external email addresses per week. Daily send quotas and rate limiting are enforced on every account. These constraints are structural — they're not policies, they're how the system works.
 
 **What about prompt injection via email?**
 
 Every inbound email includes a trust classification — trusted, agent, unverified, or suspicious — based on whether the sender is in your addressbook and whether their email passes authentication checks. This helps your agent decide how cautiously to handle each message. Emails from other InboxAPI agents are flagged separately so your agent knows to check with you before acting on them.
 
+Additionally, untrusted email content is automatically transformed using spotlighting (datamarking) — whitespace is replaced with a unique marker character so your agent can clearly distinguish email data from its own instructions. This reduces the success rate of prompt injection attacks embedded in emails from ~50% to under 3%.
+
+**What is spotlighting?**
+
+Email retrieval tools apply datamarking to untrusted content, replacing whitespace with a unique Unicode marker character generated per request. Content containing the marker should be treated as external data — never as instructions to follow. To recover the original text, replace the marker with a space. Emails from trusted senders (in your addressbook with valid authentication) are not spotlighted by default. This technique is based on academic research ([arXiv:2403.14720](https://arxiv.org/abs/2403.14720)).
+
 **What about data exfiltration?**
 
-Outbound emails are scanned for authentication tokens and credentials. If your agent accidentally tries to send an email containing a JWT or access token, the message is rejected before it leaves the platform. This prevents agents from being tricked into leaking sensitive data via email.
+Outbound emails are scanned for authentication tokens and credentials. If your agent accidentally tries to send an email containing a JWT or access token, the message is rejected before it leaves the platform. This prevents agents from being tricked into leaking sensitive data via email. Additionally, all recipient addresses in send, reply, and forward operations are validated against RFC 5322 — malformed addresses are rejected before delivery.
 
 **Can agents spam each other?**
 
@@ -250,7 +266,7 @@ Email reaches the entire existing internet — billions of people and businesses
 
 **What are the send limits?**
 
-Each account can email up to 5 unique external domains per week. Emails to other @inboxapi.ai addresses don't count against this limit. The limit resets weekly.
+Each account can email up to 5 unique external email addresses per week. Emails to other @inboxapi.ai addresses don't count against this limit. The limit resets weekly.
 
 **What happens when I hit the limit?**
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@inboxapi/cli",
-  "version": "0.2.8",
+  "version": "0.2.10",
   "description": "📧 Email for your AI 🤖",
   "main": "index.js",
   "bin": {
@@ -11,7 +11,7 @@
   ],
   "repository": {
     "type": "git",
-    "url": "git+https://github.com/shaond/inboxapi-cli.git"
+    "url": "git+https://github.com/inboxapi/cli.git"
   },
   "keywords": [
     "mcp",
@@ -27,10 +27,10 @@
     "test": "cargo test"
   },
   "optionalDependencies": {
-    "@inboxapi/cli-darwin-arm64": "0.2.8",
-    "@inboxapi/cli-darwin-x64": "0.2.8",
-    "@inboxapi/cli-linux-x64": "0.2.8",
-    "@inboxapi/cli-linux-arm64": "0.2.8",
-    "@inboxapi/cli-win32-x64": "0.2.8"
+    "@inboxapi/cli-darwin-arm64": "0.2.10",
+    "@inboxapi/cli-darwin-x64": "0.2.10",
+    "@inboxapi/cli-linux-x64": "0.2.10",
+    "@inboxapi/cli-linux-arm64": "0.2.10",
+    "@inboxapi/cli-win32-x64": "0.2.10"
   }
 }