ClawHub
Back to skill

Security audit

ClawTopics Link

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent and bounded: it installs a checksum-pinned ClawTopics Gateway plugin and allows one controlled safe restart.

Install only if you intend to connect this OpenClaw Gateway to ClawTopics/TekoAI cloud services and are comfortable with replacing/enabling the plugin plus one bounded safe Gateway restart. Operators should also know the manual recovery action may appear with a Chinese label.

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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 (1)

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The skill hard-codes a Chinese-language user interaction (`我已重启，继续检查`) without offering a language fallback or justification. In an operational recovery flow, this can confuse non-Chinese-speaking operators, increase the chance of incorrect restart handling, and delay incident recovery or safe validation steps.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/gateway-restart.mjs:135

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/install-or-upgrade.mjs:91