Back to skill

Security audit

cnn-english-learning

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward CNN English-learning helper with no hidden code, persistence, or privileged behavior.

Install this if you want CNN English article explanations in Simplified Chinese. Be aware that very short commands such as “continue” or “make it simpler” should only be routed to this skill when you are already using it for article study.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction says to default to Simplified Chinese explanations, and similar language appears again in the default settings. This imposes a language/locale preference without indicating user choice or opt-in, which matches the language policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The document instructs the skill to provide the overview in Simplified Chinese and repeats this requirement in later defaults. This is a natural-language locale restriction that is not presented as user-configurable or opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrase “继续” is extremely broad and commonly used in ordinary conversation, so it can cause accidental activation outside the intended CNN-learning context. That creates routing ambiguity and may unexpectedly steer unrelated user exchanges into this skill, especially in systems that auto-invoke skills based on phrase matching.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The phrase “简单一点” is a common conversational instruction and is too unspecific to safely identify this skill. In an agent environment with skill routing, such broad phrasing can lead to unintended invocation and confusing behavior when users are actually addressing another task.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The phrase “详细一点” is generic feedback that users may say in many unrelated conversations. If used as a standalone activation cue, it can collide with normal dialog and invoke this skill unexpectedly, causing misrouting rather than direct code or data compromise.

Content

No source excerpt is available for this finding.