ClawHub
Back to skill

Security audit

intent-router

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed paid intent-classification helper that sends provided text to a hosted endpoint, with no hidden code or destructive behavior found.

Install only if you trust the awal CLI and the hosted classifier endpoint. Use spending limits or manual review for paid calls, and avoid sending secrets, credentials, regulated data, or confidential conversations unless the service's privacy practices are acceptable to you.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The description includes very broad triggers such as "intent," "classify," "route," and "categorize," which can cause the skill to be invoked in many unrelated contexts. Because this skill sends user text to a remote paid service, overbroad invocation increases the risk of unintended data disclosure and unnecessary spend during multi-agent routing.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs users to send input text to an external endpoint but does not clearly warn that the provided text leaves the local environment and is transmitted to a third-party service. This is dangerous because users may submit sensitive conversations, personal data, or proprietary content without informed consent, especially since the skill is positioned for message routing and NLU use cases that often involve real user messages.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.