ClawHub
Back to skill

Security audit

sendmux-mailbox-agent

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Sendmux mailbox helper with sensitive email actions, but its instructions consistently require scoped credentials and user approval for sending, mutating, or deleting messages.

Install only if you intend to let an agent work with a Sendmux mailbox. Use a mailbox-scoped key, scoped agent token, or mailbox OAuth grant rather than a root key, and review exact recipients, subject, body, attachments, and any delete or mutation request before approval.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

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 for mailbox-scoped workflows with an `smx_mbx_` key, scoped `smx_agent_` token, or REST OAuth grant with Mailbox access: read, search, triage, reply when allowed, and sync one mailbox.

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
## Boundaries

- Do not ask the user to paste an API key.
- Do not use a root key for mailbox work.
- Do not create mailboxes or mailbox keys here; route those tasks to `sendmux-management`.
- Do not delete or mutate messages without explicit user confirmation.

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 49)May include surrounding context.

md
When recommending mailbox calls, name the usable credential (`smx_mbx_` key, scoped `smx_agent_` token or Mailbox OAuth), selected mailbox and required permissions before the calls. For a saved-draft workflow, include the approval boundary for the final recipients, subject, bodies and attachments even when the user only asks for preparation. For a saved-draft send or retry, state that `mailbox.read` and `email.send` authorise sending; `mailbox.drafts.write` authorises editing and cannot substitute for sending permission.

| Task                               | Preferred call                                                                                                |
| ---------------------------------- | ------------------------------------------------------------------------------------------------------------- |
| Identify the mailbox               | `mailbox_get_me`, CLI `mailbox:me:get`, SDK `mailboxGetMe`.                                                   |
| Count matching messages            | `mailbox_count_messages`, CLI `mailbox:count-messages`, SDK `mailboxCountMessages`.                           |

Static analysis

No suspicious patterns detected.