ClawHub
Back to skill

Security audit

learn-anything

Security checks for vulnerabilities and agentic risk

Overview

This is a benign educational skill for one-hour beginner crash courses, with only a minor risk that its broad trigger could activate when a user wanted a simpler answer.

Installers should expect this skill to take over many fast-learning or crash-course style requests with a fixed beginner workflow. If you prefer brief answers or advanced treatment, ask explicitly for a concise answer or say not to use the one-hour workflow.

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
96% confidence
Finding

The trigger conditions are broad enough to activate on many ordinary learning requests, which can cause the skill to engage when a more general response would be more appropriate. This increases the chance of misrouting user intent and forcing a rigid workflow, but it does not by itself enable code execution, data exfiltration, or privilege escalation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.