ClawHub
Back to skill

Security audit

Ads Brain Planning Create Pipeline 1.0.0

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed ad-campaign planning workflow with guardrails and no bundled executable code or persistence.

Install this only where a Chinese-language ad planning workflow is appropriate. Review generated campaign drafts and warnings before confirming any downstream creation action, especially budget, audience, objective, and eligibility assumptions.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger conditions are written broadly enough to match generic planning/help requests, which can cause this skill to activate outside its intended scope. In this skill’s context, unintended invocation matters because it can route users into a create pipeline that produces campaign drafts or creation parameters when they may have wanted advice, diagnosis, or another workflow instead.

Natural-Language Policy Violations

Medium
Confidence
98% confidence
Finding
Forcing all customer-facing output to Chinese without checking user locale or preference can cause misunderstandings of constraints, warnings, or next steps. In an ad-creation workflow, misread gating outcomes or assumptions can lead to incorrect confirmation, poor campaign setup decisions, or inaccessible output for non-Chinese-speaking users.

Static analysis

No suspicious patterns detected.