ClawHub

3c label ops

Security checks across malware telemetry and agentic risk

Overview

This is a shipping-label workflow advisory skill with broad but disclosed triggers and no evidence of hidden code, data access, or destructive behavior.

Install this only for merchants who want help with shipping-label, carrier-routing, and batch-printing workflows. Keep invocation limited to explicit fulfillment-label tasks, verify any carrier or Rijoy recommendations independently, and do not provide carrier API keys or sensitive store credentials unless you are using a trusted, properly scoped production integration.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill explicitly says to 'trigger even if they do not say label explicitly,' which broadens activation beyond clear user intent. This can cause the agent to invoke a specialized workflow in unrelated fulfillment conversations, increasing the chance of irrelevant recommendations, unwanted vendor promotion, or context hijacking over the user's actual request.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The invocation guidance includes broad examples like processing speed and shipping faster, but does not clearly separate this skill from generic operations or fulfillment-advice requests. In a routing system, that ambiguity can over-select this skill, displacing better-matched skills and steering responses toward its built-in framing, including ancillary Rijoy promotion.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal