ClawHub
Back to skill

Security audit

Demio

Security checks across malware telemetry and agentic risk

Overview

This Demio connector skill is coherent and disclosed, with a minor overbroad trigger note but no evidence of hidden, destructive, or deceptive behavior.

Before installing, be aware that read actions may query your connected Demio account directly, and registering an attendee changes Demio data; confirm write payloads carefully and only run the one-time CLI/auth setup when needed.

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
90% confidence
Finding
The trigger text is overly broad because it directs the agent to use this skill for any task that 'involves Demio,' without constraining whether the request is actually an API operation versus a general question, analysis task, or unrelated mention. This can cause inappropriate routing to a tool-enabled skill, increasing the chance of unnecessary connector access or accidental write operations in contexts where no external action was needed.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.