ClawHub
Back to skill

Security audit

Marketing Principles

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only marketing advice skill with no code, persistence, credential access, or privileged behavior.

Installers should treat this as a marketing strategy aid, not as a general decision-making authority; review outputs carefully when questions involve legal, medical, financial, security, or other specialized domains.

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
Confidence
95% confidence
Finding
The skill description contains broad activation cues such as 'when someone needs strategic thinking,' 'needs a framework for a tough choice,' and 'what would work here,' which can match many ordinary user requests unrelated to marketing. This can cause the skill to trigger too often, leading to inappropriate routing, overreach into domains outside its expertise, and reduced safety if strategic advice is applied in contexts like legal, medical, or security-sensitive decisions.