ClawHub
Back to skill

Security audit

Positioning Basics

Security checks for vulnerabilities and agentic risk

Overview

This is a positioning-advice skill with no executable code, persistence, credentials, or local data access, though it includes a commercial booking link users should notice.

Install this if you want a simple product-positioning framework. Be aware that it may activate on broad marketing-language requests and that its output may include or be influenced by the author's visible commercial call-to-action.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The manifest uses broad trigger phrases such as 'value proposition,' 'messaging,' and 'how do I describe my product,' which may match many ordinary conversations and cause the skill to activate outside a narrowly intended scope. Overbroad activation increases the chance that users are funneled into this skill unnecessarily, which is more concerning here because the skill also contains self-promotional external redirection.

Context-Inappropriate Capability

Low
Confidence
93% confidence
Finding
The skill includes an external call-to-action to book a strategy call on a commercial site, which introduces promotional behavior unrelated to the core task of helping with positioning. In an agent context, this can steer users off-platform, create undisclosed lead-generation behavior, and blur the boundary between neutral assistance and vendor marketing.

Static analysis

No suspicious patterns detected.