ClawHub
Back to skill

Security audit

app-ads

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow app-advertising reference guide and does not ask for unusual access or perform actions on the user's system.

Installers should understand this is an advisory marketing skill for mobile app ad campaigns. It may be invoked for broad app-promotion wording, but it does not run code or access accounts; users should still review platform-specific recommendations before spending ad budget.

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
91% confidence
Finding

The description says to use the skill when the user wants to 'promote mobile apps,' which is broader and less constrained than the surrounding product-specific trigger phrases. Without clearer boundaries or exclusion examples, this could overlap with general marketing discussions and cause unintended invocation instead of more specific related skills.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.