ClawHub
Back to skill

Security audit

Vestibular Tutor

Security checks for vulnerabilities and agentic risk

Overview

This is a Portuguese vestibular tutoring skill with broad activation wording but no evidence of hidden, destructive, persistent, or data-access behavior.

Install this if you want a strongly opinionated tutoring style for Portuguese-language vestibular study. Be aware it may take over broad 'explain this' conversations because its trigger wording is wide; narrow the trigger text if you only want it used for explicit FUVEST or school-study requests.

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 activation criteria are extremely broad, including generic phrases like 'não entendi', 'explica de novo', 'como isso funciona', and effectively 'any content question'. This can cause the skill to trigger during ordinary conversation and override more appropriate routing, leading to unintended behavior, prompt capture, or misuse of the agent in contexts outside its intended scope.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.