ClawHub
Back to skill

Security audit

sendmux-send-email

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Sendmux email-sending guide that discloses credential use, outbound transmission, attachments, and user confirmation requirements.

Install only if you intend to let an agent help send email through Sendmux. Use scoped Sendmux credentials, keep secrets out of chat, and review every sender, recipient, subject, body, and attachment before allowing a send.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 33)May include surrounding context.

md
- Do not invent recipients, sender addresses, subject lines, or body content.
- Send only after the user supplies or confirms every recipient and message.
- For batch sends, confirm the full recipient/message set before calling a send tool.
- Use a send-capable `smx_mbx_` key, owner-approved Sending-resource `smx_agent_` token, or REST OAuth grant with Sending access and `email.send` for the Sending HTTP API. SMTP requires a send-capable API key; OAuth access tokens are not SMTP or IMAP passwords.

For an agent-profile before/after approval answer, cover the complete lifecycle:

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

md
- Do not invent recipients, sender addresses, subject lines, or body content.
- Send only after the user supplies or confirms every recipient and message.
- For batch sends, confirm the full recipient/message set before calling a send tool.
- Use a send-capable `smx_mbx_` key, owner-approved Sending-resource `smx_agent_` token, or REST OAuth grant with Sending access and `email.send` for the Sending HTTP API. SMTP requires a send-capable API key; OAuth access tokens are not SMTP or IMAP passwords.

For an agent-profile before/after approval answer, cover the complete lifecycle:

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 23)May include surrounding context.

md
## ClawHub account note

This ClawHub skill connects OpenClaw agents to Sendmux. Some workflows require a Sendmux account and an appropriate Sendmux API key or agent token. Sendmux account usage is external to ClawHub; do not ask users to paste secrets into chat.

Use this skill when the user is ready to send outbound email through Sendmux or needs code/commands for sending.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 29)May include surrounding context.

md
## Safety first

- Do not ask the user to paste an API key.
- Do not invent recipients, sender addresses, subject lines, or body content.
- Send only after the user supplies or confirms every recipient and message.
- For batch sends, confirm the full recipient/message set before calling a send tool.

Whitespace Padding

Medium
Category
Prompt Injection
Confidence
70% confidence
Finding

Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Content

Scanner excerpt · SKILL.md (reported line 47)May include surrounding context.

md
## Choose the send path

| User task                                 | Efficient default                                                                                                                      |
| ----------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------- |
| One outbound email                        | `POST /emails/send`, MCP `sending_send_email`, CLI `sending:send`, or SDK `sendingSendEmail`.                                          |
| More than one independent outbound email  | Batch by default: `POST /emails/send/batch`, MCP `sending_send_email_batch`, CLI `sending:send:batch`, or SDK `sendingSendEmailBatch`. |

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 243)May include surrounding context.

Use direct HTTP only when MCP, CLI, or SDK is unavailable:

bash
curl --silent --show-error --fail-with-body \
  --config - \
  --data-binary @sendmux-email.json <<CURL_CONFIG
request = "POST"

Static analysis

No suspicious patterns detected.