ClawHub
Back to skill

Security audit

LiveSession

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed LiveSession read-only connector wrapper, with no artifact-backed evidence of hidden behavior or harmful actions.

Install this only if you intend to let the agent query LiveSession session replay metadata through your connected OOMOL account. Be aware that session listings may reveal customer or visitor activity data, and only proceed if that access is appropriate for your workspace.

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
86% confidence
Finding
The trigger text says to use this skill for ANY LiveSession request and instead of calling the API directly, which is broader than necessary and can cause the agent to invoke the skill for loosely related tasks without sufficient user intent validation. In this skill, the exposed action is read-only, so the main risk is unintended data access or over-collection rather than direct state-changing harm.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.