ClawHub
Back to skill

Security audit

Vitally

Security checks across malware telemetry and agentic risk

Overview

This skill is a clearly disclosed Vitally connector that can read and modify account data, with explicit confirmation rules for write and delete actions.

Install this only if you want agents to use your OOMOL-connected Vitally account. Review write and delete prompts carefully, especially delete_account and update_account, and only proceed when the target account and payload are exactly what you intend.

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 activation text is broad enough to route any Vitally-related request through this skill, including read, write, and destructive operations. In an agent ecosystem, overly broad routing increases the chance the skill is invoked in situations where the user did not intend connector-backed execution, which can lead to unnecessary access to customer data or accidental state changes if downstream confirmations are weak or bypassed.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.