ClawHub
Back to skill

Security audit

sendmux-cli

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Sendmux CLI guide that uses expected credentials and email/account operations, with visible safety boundaries and no hidden or destructive behavior in the artifact.

Install this only if you intend to let agents use Sendmux from the terminal. Use scoped profiles or OAuth where possible, keep API keys in your secret store or environment, review send/account-management commands before execution, and revoke/logout profiles when access is no longer needed.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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 13)May include surrounding context.

md
envVars:
      - name: "SENDMUX_ACCESS_TOKEN"
        required: false
        description: "Optional externally managed OAuth access token for CLI HTTP requests; the CLI does not refresh it."
      - name: "SENDMUX_API_KEY"
        required: false
        description: "Optional Sendmux API key or scoped agent token used by CLI, SDK, HTTP, or MCP examples."

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 40)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 terminal is the right Sendmux surface.

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 46)May include surrounding context.

md
## Boundaries

- Do not ask the user to paste API keys.
- For API-key profiles, use `smx_root_` for `management:*` and `smx_mbx_` or scoped `smx_agent_` for `mailbox:*`.
- OAuth profiles require the operation's approved surface, scopes and mailbox access. REST OAuth tokens authenticate HTTP, not SMTP or IMAP.
- Durable agent profiles can read and receive mail while active, but cannot send until an invited owner accepts and approves sending.

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 158)May include surrounding context.

md
The unpublished candidate CLI source exposes these generated operation commands. Verify its published version before relying on the new commands:

| Surface    | Count | Examples                                                                                                                                                   |
| ---------- | ----: | ---------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Management |    57 | `management:domains:list`, `management:create-domain`, `management:create-mailbox`, `management:get-spend-summary`, `management:create-webhook`            |
| Mailbox    |    52 | `mailbox:search-message-snippets`, `mailbox:batch-get-messages`, `mailbox:query-message-changes`, `mailbox:send-message`, `mailbox:list-granted-mailboxes` |

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 164)May include surrounding context.

md
| Mailbox    |    52 | `mailbox:search-message-snippets`, `mailbox:batch-get-messages`, `mailbox:query-message-changes`, `mailbox:send-message`, `mailbox:list-granted-mailboxes` |
| Sending    |     8 | `sending:get-open-api-spec`, `sending:send`, `sending:send:batch`, `sending:upload-attachment`, `sending:create-attachment-upload`, `sending:complete-attachment-upload`, `sending:get-attachment` |
| OAuth      |     2 | `auth:login`, `auth:logout` |
| Profiles   |     3 | `profiles:list`, `profiles:set`, `profiles:show`                                                                                                           |
| Agent      |     2 | `agent:register`, `agent:invite-owner`                                                                                                                      |

Use command-level help to discover accepted path, query, header, and body fields:

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 165)May include surrounding context.

md
| Sending    |     8 | `sending:get-open-api-spec`, `sending:send`, `sending:send:batch`, `sending:upload-attachment`, `sending:create-attachment-upload`, `sending:complete-attachment-upload`, `sending:get-attachment` |
| OAuth      |     2 | `auth:login`, `auth:logout` |
| Profiles   |     3 | `profiles:list`, `profiles:set`, `profiles:show`                                                                                                           |
| Agent      |     2 | `agent:register`, `agent:invite-owner`                                                                                                                      |

Use command-level help to discover accepted path, query, header, and body fields:

Static analysis

No suspicious patterns detected.