ClawHub
Back to skill

Security audit

Ads Brain Planning Pipeline 1.0.0

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill defines an ads planning workflow and confirmation states, but it does not install code, run tools, persist data, or directly execute advertising changes.

Before connecting this skill to live advertising execution, require a fresh user confirmation that clearly summarizes budget, targeting, delivery, and account-impact changes. As published, it is a planning workflow document rather than an executable integration.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill defines confirm_create and confirm_action states and allows next_action values like confirm_execution without requiring any explicit spend/account-impact warning or a hard confirmation message in the output contract. In an ads context, even if this file says it does not directly execute tools, downstream integrations could treat these states as approval-ready and cause live campaign creation or optimization changes without sufficiently informed user consent.

Content

No source excerpt is available for this finding.