@inboxapi/cli 0.2.7 → 0.2.9
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +8 -2
- package/package.json +7 -7
package/README.md
CHANGED
|
@@ -48,7 +48,7 @@ The CLI acts as a local bridge between your AI client and the [InboxAPI](https:/
|
|
|
48
48
|
|
|
49
49
|
- **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.
|
|
50
50
|
- **Weekly send limit** — Each account can send to up to five unique email addresses per week. This resets weekly.
|
|
51
|
-
- **Check your spam folder** —
|
|
51
|
+
- **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.
|
|
52
52
|
- **No attachments yet** — Attachment support is not available right now, but it's coming soon.
|
|
53
53
|
- **No rich text yet** — Emails are sent as plain text only. Rich text (HTML) support is coming soon.
|
|
54
54
|
|
|
@@ -232,9 +232,15 @@ Account creation requires proof-of-work. Each account can only email 5 unique ex
|
|
|
232
232
|
|
|
233
233
|
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.
|
|
234
234
|
|
|
235
|
+
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%.
|
|
236
|
+
|
|
237
|
+
**What is spotlighting?**
|
|
238
|
+
|
|
239
|
+
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)).
|
|
240
|
+
|
|
235
241
|
**What about data exfiltration?**
|
|
236
242
|
|
|
237
|
-
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.
|
|
243
|
+
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.
|
|
238
244
|
|
|
239
245
|
**Can agents spam each other?**
|
|
240
246
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@inboxapi/cli",
|
|
3
|
-
"version": "0.2.
|
|
3
|
+
"version": "0.2.9",
|
|
4
4
|
"description": "📧 Email for your AI 🤖",
|
|
5
5
|
"main": "index.js",
|
|
6
6
|
"bin": {
|
|
@@ -11,7 +11,7 @@
|
|
|
11
11
|
],
|
|
12
12
|
"repository": {
|
|
13
13
|
"type": "git",
|
|
14
|
-
"url": "git+https://github.com/
|
|
14
|
+
"url": "git+https://github.com/inboxapi/cli.git"
|
|
15
15
|
},
|
|
16
16
|
"keywords": [
|
|
17
17
|
"mcp",
|
|
@@ -27,10 +27,10 @@
|
|
|
27
27
|
"test": "cargo test"
|
|
28
28
|
},
|
|
29
29
|
"optionalDependencies": {
|
|
30
|
-
"@inboxapi/cli-darwin-arm64": "0.2.
|
|
31
|
-
"@inboxapi/cli-darwin-x64": "0.2.
|
|
32
|
-
"@inboxapi/cli-linux-x64": "0.2.
|
|
33
|
-
"@inboxapi/cli-linux-arm64": "0.2.
|
|
34
|
-
"@inboxapi/cli-win32-x64": "0.2.
|
|
30
|
+
"@inboxapi/cli-darwin-arm64": "0.2.9",
|
|
31
|
+
"@inboxapi/cli-darwin-x64": "0.2.9",
|
|
32
|
+
"@inboxapi/cli-linux-x64": "0.2.9",
|
|
33
|
+
"@inboxapi/cli-linux-arm64": "0.2.9",
|
|
34
|
+
"@inboxapi/cli-win32-x64": "0.2.9"
|
|
35
35
|
}
|
|
36
36
|
}
|