Security audit

sendmux-getting-started

Security checks for vulnerabilities and agentic risk

Overview

This Sendmux setup skill is coherent and disclosed, but users should treat package installs, API keys, and saved agent profiles with normal care.

Before installing, verify the Sendmux package sources, prefer least-privileged keys or OAuth scopes, keep secrets in environment variables or a secret manager, and understand that self-registration saves a durable read profile until it is revoked.

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 (8)

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 29)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 to get a user from "I have a Sendmux task" to the correct surface, key kind, package, and first verified call.

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 35)May include surrounding context.
md
## Safety first - Do not ask the user to paste an API key. - Do not print API keys. - Prefer existing environment variables, permission-restricted local CLI profiles, or the user's secret manager. Authorised profile and secret-store files are expected credential storage, not a leak. - For self-registration, let the CLI create and persist the agent profile; never copy its raw credential into chat, logs, prompts, screenshots, or repo files.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 89% confidence
Finding: The skill instructs users to run npx skills add Sendmux/skills without pinning a specific package version or commit. This creates a supply-chain risk because the fetched package may change over time or be replaced by a compromised release, causing users to install unreviewed code.
Content: No source excerpt is available for this finding.

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 56)May include surrounding context.
md
For user-approved access to an existing account, use OAuth login through `sendmux-cli`. REST OAuth grants can cover multiple API surfaces and mailboxes with explicit scopes; hosted MCP and A2A retain separate OAuth resources. The table below describes API-key credentials and the separate agent self-registration flow. | Task | Key prefix | Start here | | --------------------------------------------------------------------------------------- | ----------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------ | | Send email through the Sending API | Send-capable `smx_mbx_` or owner-approved Sending-resource `smx_agent_` | `sendmux-send-email` for real sends; this skill can verify package/API discovery first. | | Read, search, sync, triage, or reply from one mailbox | `smx_mbx_` or scoped `smx_agent_` | Mailbox MCP, CLI, or SDK. |

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 56)May include surrounding context.
md
For user-approved access to an existing account, use OAuth login through `sendmux-cli`. REST OAuth grants can cover multiple API surfaces and mailboxes with explicit scopes; hosted MCP and A2A retain separate OAuth resources. The table below describes API-key credentials and the separate agent self-registration flow. | Task | Key prefix | Start here | | --------------------------------------------------------------------------------------- | ----------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------ | | Send email through the Sending API | Send-capable `smx_mbx_` or owner-approved Sending-resource `smx_agent_` | `sendmux-send-email` for real sends; this skill can verify package/API discovery first. | | Read, search, sync, triage, or reply from one mailbox | `smx_mbx_` or scoped `smx_agent_` | Mailbox MCP, CLI, or SDK. |

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 59)May include surrounding context.
md
| Task | Key prefix | Start here | | --------------------------------------------------------------------------------------- | ----------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------ | | Send email through the Sending API | Send-capable `smx_mbx_` or owner-approved Sending-resource `smx_agent_` | `sendmux-send-email` for real sends; this skill can verify package/API discovery first. | | Read, search, sync, triage, or reply from one mailbox | `smx_mbx_` or scoped `smx_agent_` | Mailbox MCP, CLI, or SDK. | | Manage domains, mailboxes, mailbox keys, providers, webhooks, logs, billing, or metrics | `smx_root_` | Management MCP, CLI, or SDK. | | Let an agent register itself and invite its owner | No existing key | CLI `agent:register`, then `agent:invite-owner` when the owner was not invited during registration. |

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 60)May include surrounding context.
md
| --------------------------------------------------------------------------------------- | ----------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------ | | Send email through the Sending API | Send-capable `smx_mbx_` or owner-approved Sending-resource `smx_agent_` | `sendmux-send-email` for real sends; this skill can verify package/API discovery first. | | Read, search, sync, triage, or reply from one mailbox | `smx_mbx_` or scoped `smx_agent_` | Mailbox MCP, CLI, or SDK. | | Manage domains, mailboxes, mailbox keys, providers, webhooks, logs, billing, or metrics | `smx_root_` | Management MCP, CLI, or SDK. | | Let an agent register itself and invite its owner | No existing key | CLI `agent:register`, then `agent:invite-owner` when the owner was not invited during registration. | For API-key authentication, use separate Management and Mailbox keys with separate clients or profiles. Do not use a root key for mailbox-scoped examples.

Static analysis

No suspicious patterns detected.