Security audit

Ielts Practice

Security checks for vulnerabilities and agentic risk

Overview

This is a focused IELTS practice skill with limited local state tracking and no evidence of hidden code, credential access, network fetching, or destructive behavior.

Before installing, be aware that the skill keeps a small local progress file to rotate daily IELTS topics. It should not need network access, credentials, or broad filesystem access for its stated purpose.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Natural-Language Policy Violations

Medium

Confidence: 84% confidence
Finding: The README defines the skill under an "English" section without indicating that users may choose another language or that English-only operation is required for a documented reason. Because locale and language constraints should be opt-in or clearly justified, this presents a natural-language policy concern.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The example trigger phrases are broad enough to match ordinary user requests such as asking for IELTS help or a workflow, which can cause the skill to activate more often than intended. This is primarily a scope/dispatch risk rather than a direct security exploit, but it can lead to unintended invocation, prompt-routing mistakes, or the skill being applied in contexts where a more appropriate policy or tool should handle the request.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The instruction 'Keep all practice content in English' imposes a fixed language policy. Under the stated rule, forcing a specific language without offering user choice or documenting a justified locale constraint is a natural-language policy violation.

Missing User Warnings

Low

Confidence: 78% confidence
Finding: The markdown instructs the skill to overwrite `memory/ielts-state.md` after each session, which is a file write affecting persisted state. The document does not explicitly warn the user that the skill will modify a local memory file or maintain session state on disk.

Static analysis

No suspicious patterns detected.