Back to skill

Security audit

Video Dubbing

Security checks for vulnerabilities and agentic risk

Overview

This skill provides guidance and a local helper for using a third-party video dubbing site, with no hidden uploads, persistence, or destructive behavior found.

Before installing, understand that this skill mainly points you to VideoAny and may run a local helper script that prints instructions. Do not upload private, copyrighted, or unauthorized media to the external service, and set the target language explicitly if you do not want the default Spanish setting.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (2)

Lp4

Low
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill requests shell:exec even though the documented behavior is only to print guidance and redirect users to an external website. Unused execution permissions violate least privilege and expand the attack surface: if the skill is later modified, misrouted, or invoked through a compromised helper script, the agent would already hold command-execution capability unnecessarily.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The script sets DEFAULT_TARGET_LANG = "es", so users who do not explicitly choose a language are guided toward Spanish by default. This is a natural-language locale choice embedded in the skill behavior, and the file does not indicate user opt-in or a documented justification for this specific default.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.