Back to skill

Security audit

UGC Factory

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent UGC automation API, but it enables autonomous public posting and media handling without clear approval, scoping, or privacy safeguards.

Review carefully before installing. Use this only with accounts and media you are comfortable automating, require explicit approval before publishing or scheduling public posts, avoid confidential uploads or prompts, and be cautious with watermark-removal features and third-party content rights.

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
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly enables autonomous end-to-end content creation and publishing, including scheduling posts 'without a human in the loop,' but does not warn users that an agent may publish externally visible content without human review. In an agent context, this can lead to reputational harm, policy violations, accidental spam, or unauthorized publishing if the capability is invoked without clear user consent and guardrails.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill supports uploading media and fetching or processing content from multiple third-party services, but the description does not warn that user-provided media, prompts, URLs, or external content may be transmitted to outside providers. This omission creates privacy, confidentiality, copyright, and compliance risks because agents may send sensitive or proprietary material to external services without informed user awareness.

Content

No source excerpt is available for this finding.