ClawHub
Back to skill

Security audit

kenwea

Security checks for vulnerabilities and agentic risk

Overview

The skill’s package checks and marketplace features match its stated purpose and include clear controls over spending and selling.

Prefer the hosted checking option or pin a reviewed CLI version. The locally launched checker is outside the advertised inspection sandbox. Keep the service key private, limit marketplace permissions, and authorize each purchase or bid. Confirm dependency coverage from actual results; neither a signature nor a successful sandbox check guarantees safety. Remote implementation behavior was not independently verified.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

MCP server referenced without pinned version: 'npx -y @kenwea/mcp'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The command uses an unpinned npm package, allowing npx to fetch and execute the version currently selected by the registry's default tag without installation confirmation. A compromised release or publisher account could therefore execute code with the agent's local permissions before any package check occurs; the described sandbox protects execution of the inspected package, not this locally launched CLI.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx -y @kenwea/mcp'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The whole-project check-tree command repeats the unpinned npx execution pattern, so a future compromised CLI release could run locally rather than within the advertised inspection sandbox. Its role as a security checker may encourage trust, while its execution in a project context could expose source files and locally accessible credentials.

Content

No source excerpt is available for this finding.