ClawHub
Back to skill

Security audit

cnn-english-learning-three

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language educational skill for close reading CNN English text, with no code execution, data access, persistence, or hidden system behavior.

Install this if you want CNN English passages explained in Chinese with detailed vocabulary and grammar breakdowns. Users who need English-only or bilingual output may need to explicitly ask for that, because the skill defaults heavily toward Chinese explanations.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill consistently mandates Chinese-language output and translation behavior without indicating that users can choose another language. This can override user preference or accessibility needs and may cause the agent to ignore higher-level user intent, which is a real policy/quality issue even though it is not a traditional security exploit. In this educational context, the risk is limited because the behavior is instructional rather than privileged or system-interacting.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.