ClawHub
Back to skill

Security audit

Pomelli AI Brand Marketing Companion

Security checks across malware telemetry and agentic risk

Overview

This is a document-only marketing helper with no executable code, API access, credential use, or persistence.

Safe to install from the reviewed artifacts. Be aware it may activate for broad marketing-related requests, and review any external Pomelli or GitHub links before sharing confidential brand, product, or campaign information outside 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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
This manifest uses generic trigger phrases such as "brand marketing," "ai marketing," "brand book," and generator-related terms without narrowing context or giving exclusion conditions. These phrases are broad enough to overlap with ordinary marketing discussions, increasing the chance of accidental invocation.

Natural-Language Policy Violations

Low
Confidence
85% confidence
Finding
The manifest sets the skill language to "en" with no indication that users can opt into another language or that the English-only constraint is required for a documented regional or compliance reason. This can be a natural-language policy issue when a skill unconditionally fixes a locale.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal