Back to skill

Security audit

Video Publish All

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only skill for guiding video publishing to four named platforms, with public-posting risk that users should confirm before use.

Before installing, understand that this skill is meant to help publish videos publicly across multiple third-party accounts. Review the video, title, description, hashtags, target platforms, and account consequences before allowing any publish action, especially all-platform posting.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill encourages posting to several external platforms but does not warn users about privacy exposure, account penalties, content-policy violations, or the consequences of duplicate distribution. In this context, the omission is material because the skill is designed for cross-platform publishing and could cause users to share sensitive content or trigger moderation/account issues without informed consent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The full-platform trigger phrase is broad enough that ordinary user language like asking to 'publish to all platforms' could invoke high-impact actions across multiple third-party accounts without sufficient confirmation. In this skill’s context, that is risky because publishing is irreversible or account-affecting, and the skill also advertises automatic platform selection, which increases the chance of unintended mass posting.

Content

No source excerpt is available for this finding.