Back to skill

Security audit

LinkedIn Carousel Factory

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward content-drafting workflow with disclosed local draft saving and Discord notification steps, but users should be aware it has side effects beyond returning text.

Install this only if you want the agent to save carousel drafts into the named Obsidian vault path and notify the specified Discord task channel. Review or adjust those destinations if they do not match your environment, and require confirmation before posting to Discord if topic privacy matters.

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
95% confidence
Finding

The skill explicitly instructs the agent to write output to a fixed local filesystem path under the user's home directory without any prompt, confirmation, or disclosure. Even though the content is low-risk marketing material, silent file creation/modification is a real side effect that can surprise users, overwrite data, or be chained with other skills to persist unwanted content.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs the agent to post a message to a Discord channel, which is an external transmission, without user consent or clear warning. Although the message is only a status update, it still leaks activity and topic metadata to a third-party service and normalizes autonomous outbound communication.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.