Security audit

Wheel of Fortune

Security checks for vulnerabilities and agentic risk

Overview

This skill simply helps create a visible decision-wheel link, with a minor privacy consideration because option text is placed in a third-party URL.

Before installing, understand that any option text included in the generated link may be sent to the external wheel website when opened. Use generic labels for personal, confidential, workplace, medical, financial, or otherwise sensitive choices.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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)

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill instructs the agent to place user-provided option labels directly into a third-party URL, but it does not warn that those labels will be disclosed to an external site when the user clicks the link. This can unintentionally expose sensitive preferences, names, locations, or other private data embedded in the options, especially because the skill encourages copying user input verbatim into the query string.

Static analysis

No suspicious patterns detected.