ClawHub
Back to skill

Security audit

Reading

Security checks for vulnerabilities and agentic risk

Overview

This skill only provides reading and book-advice guidance and does not request sensitive access or unsafe actions.

This skill is appropriate if you want the agent to give more structured reading, retention, and book-recommendation advice. Be aware it may activate for general reading-related requests, but it does not add code execution, data access, persistence, or account permissions.

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

Low
Confidence
85% confidence
Finding
The description says the skill will 'Help users read better,' which is a broad natural-language trigger that can overlap with many everyday requests about reading, books, or learning. The file does not provide clearer activation constraints, explicit trigger phrases, or negative examples to narrow when this skill should be invoked.

Static analysis

No suspicious patterns detected.