ClawHub
Back to skill

Security audit

Deep Ads Research

Security checks for vulnerabilities and agentic risk

Overview

This is a plain advertising research planning skill with somewhat broad trigger wording but no code, credential access, persistence, or privileged actions.

Install this if you want structured research plans for advertising decisions. Be aware it may activate on broad growth or revenue marketing prompts, so users may need to clarify when they want general business advice instead of ads-specific research orchestration.

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The activation criteria mix broad outcome-oriented requests like growth, revenue, and profit with a much narrower skill purpose, making it unclear when this skill should be selected. That ambiguity can cause unintended invocation and inappropriate delegation, especially in multi-skill environments where broad business requests should be handled by more general planning or analysis skills.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger keyword list is broad enough to match many ordinary business or marketing conversations, which can cause this skill to activate outside its intended niche. Over-triggering is risky because it can route users into ads-specific research orchestration when they wanted more general advice, leading to irrelevant guidance, hidden tool usage, or reduced reliability of the agent’s behavior.

Static analysis

No suspicious patterns detected.