Back to skill

Security audit

Groundmail Agent Mailboxes

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because it repeatedly runs the Groundmail CLI through unpinned `npx` commands, creating a risk that a changed or compromised package could access credentials or other resources available to the agent.

Consider installing only after verifying the CLI package and fixing it to a specific reviewed version. Limit the credentials and local access available to it. The scan was partial: it inspected the listed Markdown component, but some references could not be resolved, so the evidence is incomplete. A separate scan completed without findings.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

MCP server referenced without pinned version: 'npx envVars'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx groundmail-cli'.

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

Although this is a CLI command rather than an MCP server configuration, npx groundmail-cli can fetch and execute an unpinned package version. A compromised release could run with the agent's local permissions and access available files or credentials; mailbox-scoped keys reduce API exposure but do not sandbox the executable.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx groundmail-cli'.

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

The ownership command executes groundmail-cli without a fixed package version, allowing a fetched release to change independently of the skill. A compromised release could access the mailbox API key, owner email address, and other resources available to the agent process.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx groundmail-cli'.

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

The verification command uses an unpinned npm executable, so a compromised fetched release could execute arbitrary code with the agent's permissions. This step also handles a verification code and mailbox credentials, increasing the sensitivity of data exposed to the executable.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx groundmail-cli'.

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

The login instruction can fetch and execute an unpinned CLI during an authentication workflow. A compromised package could capture authentication material or access local resources; workspace login may expose broader authority than the mailbox-scoped workflow, depending on the credentials granted.

Content

No source excerpt is available for this finding.