ClawHub
Back to skill

Security audit

Cognitive Load Theory

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only instructional design skill with broad but disclosed activation language and no privileged actions.

Installers should be aware the skill may activate for general complaints about confusing or overwhelming material, but the artifact is otherwise coherent and limited to educational design guidance.

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
93% confidence
Finding

The skill defines many broad, natural-language activation triggers such as 'this is overwhelming,' 'hard to follow,' and 'working memory,' which are likely to appear in ordinary support, onboarding, documentation, or UX conversations. This can cause over-activation and unintended routing, leading the agent to apply this skill in contexts where it is only loosely relevant and potentially displacing a more appropriate skill or response strategy.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.