ClawHub
Back to skill

Security audit

Intelliprint

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a read-oriented Intelliprint connector with clean telemetry, but its routing language is broader than ideal.

Before installing, confirm the skill is only used for Intelliprint read/search tasks you ask for. Avoid relying on it for unsupported or state-changing Intelliprint work unless the skill documentation clearly lists those actions and requires explicit confirmation.

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 (1)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The description says to use this skill for ANY Intelliprint request and instead of calling the API directly, which is an overly broad routing trigger. This can cause the agent to invoke the skill in situations it should not, including requests that exceed the skill’s documented read-only action set or that would be better handled with narrower, safer logic, increasing the chance of unintended tool use and over-collection of data.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal