Back to skill

Security audit

SocialKit YouTube Visuals

Security checks for vulnerabilities and agentic risk

Overview

This skill plans video visuals and writes a project shot list, with no bundled code or hidden account actions.

Use this skill with an approved script in a dedicated project folder. Visual planning needs no Google credentials. Both supplied scanners reported no findings; independent inspection of all three bundled files resolved the scanner's missing-reference gaps as expected project inputs and outputs. Companion skills and their authorization scripts remain outside this review.

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