Back to skill

Security audit

YouTube KOL finder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed YouTube creator research workflow that gathers public or provider-sourced business contacts but does not send outreach or install code.

Before installing, confirm that you actually need business contacts, use the shortlist-only mode when contacts are unnecessary, and ensure any collected creator emails are used only for lawful, policy-compliant business outreach. Review Glasser costs and provider terms because this skill can use paid data lookups.

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
87% confidence
Finding

The skill explicitly guides collection and enrichment of creator business contact information, including use of paid enrichment when free public sources do not resolve an address, but it does not present a clear privacy warning or consent/appropriate-use notice to the user. Even though it limits scope to business contacts and discourages guessing private emails, the workflow still enables privacy-sensitive aggregation of personal/professional contact data and could be misused for unsolicited outreach or profiling.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.