ClawHub
Back to skill

Security audit

Meta Ads Recommendation

Security checks for vulnerabilities and agentic risk

Overview

This skill only turns existing Meta Ads analysis into bounded recommendations and does not install code, call external services, or make changes itself.

Before installing, be comfortable with the skill reading Meta Ads campaign analysis context in the current session. Review its suggested pauses or budget changes before applying them manually in Meta Ads Manager.

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
  • 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
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill’s routing description is broad enough to trigger on many generic requests for campaign advice, making it a likely catch-all endpoint. In a multi-skill agent, this can cause inappropriate invocation without required prior analysis context, leading to recommendations based on incomplete or stale session data and reducing reliability of downstream decisions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.