Back to skill

Security audit

Xobni Email

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only email API skill whose sensitive capabilities are broadly disclosed and aligned with its stated purpose.

Before installing, understand that this skill can let an agent read and send email, access attachment contents, and create persistent webhooks that forward email metadata and snippets. Use a narrowly scoped API key, confirm recipients before sending, and only configure webhook URLs you control and trust.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (17)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/api.md (reported line 142)May include surrounding context.

Delete Webhook

text
DELETE /event-hooks/{id}

List Deliveries

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill enables high-risk actions—reading inbox contents, sending email, handling attachments, and configuring webhooks—but the description does not warn users that sensitive communications and metadata may be accessed or transmitted. In an agent context, lack of explicit consent and privacy warnings can lead to unintended disclosure of email content and misuse of outbound messaging capabilities.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.

Read Inbox

bash
curl -H "Authorization: Bearer $XOBNI_KEY" \
  "https://api.xobni.ai/api/v1/emails?status=received&limit=20"

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The webhook section states that payloads include email metadata and a 200-character snippet, but it does not warn that this data will be transmitted to third-party endpoints chosen by the operator. That omission increases the chance that users expose sensitive sender, subject, or partial body content to systems that are less trusted or improperly secured.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

Creating a webhook sends email event data to an arbitrary external URL, which can become a data-exfiltration path if misconfigured or pointed at an untrusted endpoint. In this skill, that risk is elevated because the webhook payload includes email metadata and snippets, yet the example does not emphasize the sensitivity of what is being forwarded.

Content

Scanner excerpt · SKILL.md (reported line 123)May include surrounding context.

Set up real-time notifications when emails arrive or are sent:

bash
curl -X POST -H "Authorization: Bearer $XOBNI_KEY" \
  -H "Content-Type: application/json" \
  "https://api.xobni.ai/api/v1/event-hooks" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
92% confidence
Finding

This webhook example forwards email event information to a user-specified external endpoint, creating a real possibility of sensitive metadata leakage or unintended onward sharing. Because the skill processes real email and explicitly includes snippets in webhook payloads, the context makes this more dangerous than a generic webhook example.

Content

Scanner excerpt · SKILL.md (reported line 125)May include surrounding context.

bash
curl -X POST -H "Authorization: Bearer $XOBNI_KEY" \
  -H "Content-Type: application/json" \
  "https://api.xobni.ai/api/v1/event-hooks" \
  -d '{
    "url": "https://your-endpoint.com/webhook",
    "events": ["email.received"],

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 32)May include surrounding context.

md
# Xobni.ai REST API Reference

Base URL: `https://api.xobni.ai/api/v1`

All requests require `Authorization: Bearer YOUR_API_KEY` header.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 41)May include surrounding context.

md
# Xobni.ai REST API Reference

Base URL: `https://api.xobni.ai/api/v1`

All requests require `Authorization: Bearer YOUR_API_KEY` header.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

md
# Xobni.ai REST API Reference

Base URL: `https://api.xobni.ai/api/v1`

All requests require `Authorization: Bearer YOUR_API_KEY` header.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

md
# Xobni.ai REST API Reference

Base URL: `https://api.xobni.ai/api/v1`

All requests require `Authorization: Bearer YOUR_API_KEY` header.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 70)May include surrounding context.

md
# Xobni.ai REST API Reference

Base URL: `https://api.xobni.ai/api/v1`

All requests require `Authorization: Bearer YOUR_API_KEY` header.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 83)May include surrounding context.

md
# Xobni.ai REST API Reference

Base URL: `https://api.xobni.ai/api/v1`

All requests require `Authorization: Bearer YOUR_API_KEY` header.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 90)May include surrounding context.

md
# Xobni.ai REST API Reference

Base URL: `https://api.xobni.ai/api/v1`

All requests require `Authorization: Bearer YOUR_API_KEY` header.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 96)May include surrounding context.

md
# Xobni.ai REST API Reference

Base URL: `https://api.xobni.ai/api/v1`

All requests require `Authorization: Bearer YOUR_API_KEY` header.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/api.md (reported line 3)May include surrounding context.

md
# Xobni.ai REST API Reference

Base URL: `https://api.xobni.ai/api/v1`

All requests require `Authorization: Bearer YOUR_API_KEY` header.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file documents a POST /emails/send operation that transmits message bodies, recipient addresses, and base64-encoded attachments, but it does not include any warning about privacy, data handling, or the impact of sending user content through the API. Under the markdown-specific SQP-2 criteria, behaviors affecting user data or privacy should be disclosed to users.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The Create Webhook section allows forwarding email events to a user-specified URL, and later sections show payloads containing sender/recipient addresses, subject lines, and body snippets. The documentation does not warn that configuring a webhook causes ongoing transmission of potentially sensitive mailbox data to an external endpoint, which is a privacy- and integrity-relevant behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.