Back to skill

Security audit

MiniMax Media

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward MiniMax media-generation helper with no packaged executable code, persistence, hidden data access, or destructive behavior, though users should notice it may route generic media requests through MiniMax.

Install this only if you are comfortable using MiniMax for media generation. Expect prompts, reference images, and generation requests to be sent to the MiniMax API, and verify output paths and API billing before use; non-Chinese users may need to ask the agent to translate errors.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill description uses very broad trigger terms such as general media-generation phrases and a 'single unified entrypoint,' which can cause the agent to invoke this skill for many common requests that may not specifically require MiniMax. Over-broad routing increases the chance of unintended tool use, unnecessary exposure of API-backed capabilities, and reduced user control over which external service is used.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

Forcing Chinese-language error reporting without user opt-in can mislead or hinder users who do not understand Chinese, especially when failures involve authentication, billing, or malformed responses. In an agent setting, this degrades transparency and can delay appropriate user action or troubleshooting.

Content

No source excerpt is available for this finding.