ClawHub
Back to skill

Security audit

Alphagbm Alert

Security checks across malware telemetry and agentic risk

Overview

This is a non-executable AlphaGBM alert-management skill whose create, edit, and delete alert behavior is disclosed and purpose-aligned.

Review the trigger phrases before installing if you use other finance or notification skills. For safety, require explicit confirmation before deleting or modifying alerts and ensure any AlphaGBM API access is limited to alert management.

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 phrases are broad and natural-language-like, including generic requests such as 'set price alert', 'my alerts', and 'delete alert'. In an agent environment, this can cause the skill to activate on ordinary conversation or collide with other finance or notification skills, leading to unintended alert creation, modification, or deletion.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.