ClawHub

Adspirer Ads Agent

Security checks across malware telemetry and agentic risk

Overview

This is a high-impact ad-management skill, but the sensitive capabilities are disclosed, purpose-aligned, and guarded by explicit confirmation and paused-campaign rules.

Install only if you want an agent connected to real ad accounts. Before using write actions, verify the selected account, review proposed changes, keep campaigns paused until approved, and provide only public creative URLs you intentionally want uploaded to your ad accounts.

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
The manifest description advertises broad natural-language control over ad campaign management without defining clear activation boundaries, approval gates, or task constraints. In a high-impact domain like paid advertising, ambiguous invocation scope can cause the agent to perform sensitive analysis or account-changing actions when user intent is underspecified, increasing the risk of unintended spend, campaign edits, or cross-account mistakes.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The manifest states that the skill can create campaigns and optimize budgets but provides no user-facing warning that these actions can directly spend money, alter live delivery, or degrade business performance. Because this skill operates on live advertising platforms across multiple networks, missing warnings and safeguards make accidental or misunderstood destructive changes materially more dangerous than in a low-impact domain.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal