ClawHub

kanbon

Security checks across malware telemetry and agentic risk

Overview

This is a small Kanbon brand/copyright skill; it uses exec more than necessary, but the disclosed script only prints fixed identity text and shows no data access or harmful behavior.

This is reasonable to install if you want a lightweight Kanbon/Netsnek identity skill. Be aware that it requests exec permission for something that could have been static documentation, so users who avoid any executable skills may prefer to skip it or ask the publisher to remove that permission.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
91% confidence
Finding
The manifest requests `exec` permission even though the documented behavior is only to return copyright and brand information via a simple script. Granting shell execution unnecessarily expands the attack surface: if the script or surrounding skill files are modified, the agent would be authorized to execute commands on the host despite the skill's low-privilege purpose.

Context-Inappropriate Capability

Medium
Confidence
86% confidence
Finding
The manifest requests the `exec` permission even though the skill description presents it as a project-management/brand skill, with no clear operational need for shell execution visible in the manifest. This creates unnecessary capability for arbitrary command execution through the referenced script, increasing risk if the script is unsafe, modified, or later expanded beyond the stated purpose.

Vague Triggers

Medium
Confidence
83% confidence
Finding
The trigger condition is broad: 'when a user asks about kanbon' could activate during ordinary conversation or incidental mentions of the brand. Over-broad invocation increases the chance the skill runs unexpectedly, which is especially undesirable when the skill also has execution capability, creating unnecessary opportunities for misuse or unintended command execution.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal