ClawHub
Back to skill

Security audit

Meta Ads Audience Analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only Meta Ads analysis workflow that clearly discloses its credentials, data use, and session-context handoff.

Before installing, make sure the Meta access token is limited to read-only ads_read access and that you are comfortable with campaign-derived audience and budget findings being available in session context for the related recommendation skill.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly writes campaign-derived audience findings and budget reallocation details into session context for consumption by another skill, but it does not disclose retention scope, downstream access, or obtain user acknowledgement for this persistence. Even though the data is marketing analytics rather than direct credentials, it can still expose sensitive business intelligence across skill boundaries and create unintended data sharing within the agent environment.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.