ClawHub
Back to skill

Security audit

Meta Ads Publisher

Security checks for vulnerabilities and agentic risk

Overview

This skill openly manages Meta Ads, but it can make spend-affecting account changes through broad instructions, so users should review and tightly control it before installation.

Install only if you intend to let the agent operate a Meta Ads account. Use a least-privileged token for the intended ad account, keep new campaigns paused until human review, and require explicit confirmation of the ad account, object IDs, budget, status, and exact change before any create, duplicate, budget, pause, or activate action.

SkillSpector

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
88% confidence
Finding
The skill description is broad enough to trigger on generic campaign-management requests without clearly constraining scope, confirmation requirements, or allowed operations. Because this skill performs real-world state-changing advertising actions, overbroad routing increases the chance of unintended campaign creation, edits, budget changes, or activation.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The when-to-use guidance lacks clear activation constraints and exclusions, so the agent may invoke this skill for loosely related requests. In a high-impact ad-management context, ambiguous triggering can cause unauthorized or mistaken ad operations against a live ad account.

Static analysis

No suspicious patterns detected.