ClawHub
Back to skill

Security audit

Agente Ingles

Security checks for vulnerabilities and agentic risk

Overview

This is a simple FUVEST English reading-prep skill with no code, network access, credential use, or persistence.

Safe to install for FUVEST English preparation. Be aware it is tailored to Antonio's study context and may activate for some general academic English reading requests, so users who want only exam-specific activation may prefer a narrower trigger.

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
Category
Not specified by scanner
Confidence
78% confidence
Finding

The manifest says to activate when Antonio mentions 'Inglês da FUVEST' or needs to practice reading academic texts in English. The second condition is broader than the narrowly defined FUVEST exam-prep scope and could overlap with ordinary study or work-related reading requests, without negative examples or boundaries.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.