ClawHub
Back to skill

Security audit

Agente Historia Geografia

Security checks for vulnerabilities and agentic risk

Overview

This is a small educational History and Geography tutoring skill with no executable code, persistence, credential access, or hidden data movement.

Installers should understand that this skill may activate for broad History, Geography, Brazil, or historical-event conversations. It is otherwise a low-risk tutoring prompt with no executable behavior observed.

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 rule is broad enough to trigger on common educational conversation, because it fires on generic terms like 'História', 'Geografia', 'Brasil', and even 'qualquer evento histórico'. Over-broad activation can cause unintended routing, context pollution, and unnecessary invocation of this skill when the user did not intend to engage it, especially in a multi-agent system with several overlapping academic domains.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.