Back to skill

Security audit

raffle-winner-picker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward raffle winner picker, with expected handling of participant names and contact details but limited privacy guidance.

Installers should treat this as benign, but when using it with spreadsheets or Google Sheets, only provide columns needed to select and contact winners, avoid sharing full emails or comments publicly, and retain exported winner records only as long as necessary.

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
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill’s example output and workflows explicitly display winner names, email addresses, comments, and row numbers, and suggest exporting or emailing winner details without any privacy warning, minimization guidance, or consent check. In a raffle/giveaway context, this can lead users to unnecessarily expose personally identifiable information from spreadsheets or Google Sheets to operators, audiences, or downstream tools.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.