ClawHub
Back to skill

Security audit

Let Me Know

Security checks across malware telemetry and agentic risk

Overview

This progress-notification skill is mostly coherent, but it can tell an agent to restart the gateway if reminder cleanup gets stuck, which is too powerful without explicit approval.

Review before installing. The notification behavior is useful and mostly well scoped, but require explicit approval or remove the gateway restart fallback, and make sure progress messages use the user's language and avoid sending sensitive log details.

SkillSpector

By NVIDIA
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)

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The skill hard-requires a Chinese pre-flight message, which can override the user's preferred language and cause important status information to be delivered in a language the user may not understand. While this is not a code-execution or privilege-escalation issue, it is a genuine security/usability weakness because users may miss or misunderstand task start, progress, or failure notifications.

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The heartbeat and failure templates are also mandated only in Chinese, reinforcing a fixed-locale policy for operational updates. In long-running or failing tasks, this can reduce the user's ability to understand current status and respond appropriately, especially if the user does not read Chinese.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.