ClawHub
Back to skill

Security audit

Aibrary Foryou Topic

Security checks for vulnerabilities and agentic risk

Overview

This skill only gives personalized book-topic recommendations, with a minor over-activation risk from broad trigger wording.

Before installing, be aware that the skill may activate for general learning-inspiration requests and may ask for personal context such as interests, career stage, goals, and recent learning activity. Install it if you are comfortable sharing that context for book-topic recommendations.

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 skill description includes broad triggers such as when the user 'wants inspiration', 'seems undecided', or asks general questions like 'what should I learn today', which can match ordinary conversation outside the skill's narrow purpose. This can cause over-activation or inappropriate proactive invocation, leading the agent to collect user profile details or steer responses toward this skill when not clearly requested.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.