ClawHub
Back to skill

Security audit

cleimesh-mcp

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a coherent, user-controlled security setup, with installation risks and native-server limitations users should understand.

Review and verify a specific installer release before running it, and pin the native server package version. Confirm only the directories and network access you intend to grant. Wrapped servers retain ordinary OS access, so use process isolation when needed. This review covers the complete bundled instruction file; the external executable and its security guarantees remain unverified.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Chaining Abuse

High
Category
Tool Misuse
Confidence
98% confidence
Finding

Piping the downloaded response directly into sh turns remotely supplied content into immediate shell execution without a verification step. This is the execution component of the same issue reported by SC2, not a separate exploit or evidence of malicious chaining; it runs before the advertised MCP protections are configured.

Content

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

1. Install (user runs it)

sh
curl -fsSL https://github.com/cleitonaugusto/cleimesh/releases/latest/download/install.sh | sh

Check: cleimesh --version.

MCP server referenced without pinned version: 'uvx mcp-server-fetch'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The command resolves and executes mcp-server-fetch without an explicit version, allowing upstream changes or a compromised release to introduce unexpected code. The skill explicitly states that wrapped servers are not sandboxed, so a malicious package could access files and network resources available to its OS user despite token-level checks.

Content

No source excerpt is available for this finding.

External Script Fetching

Low
Category
Supply Chain
Confidence
99% confidence
Finding

The installation command retrieves a mutable latest-release script and executes it without checking a pinned version, signature, or independently trusted digest. A compromised repository or release could therefore execute attacker-controlled code with the user's privileges; requiring the human to run the command reduces autonomous execution but does not remove the supply-chain exposure.

Content

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

1. Install (user runs it)

sh
curl -fsSL https://github.com/cleitonaugusto/cleimesh/releases/latest/download/install.sh | sh

Check: cleimesh --version.