Security audit

MiniMax Vision Analysis

Security checks for vulnerabilities and agentic risk

Overview

The skill is for legitimate image analysis, but it needs Review because it can automatically send local images to MiniMax and relies on an unpinned MCP server package.

Install only if you are comfortable sending selected images, including any visible text, to MiniMax for processing. Avoid confidential screenshots or documents unless your policy allows it, restrict MCP file access where possible, use a limited API key, and prefer a pinned, reviewed MCP package version.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T08 · Insecure Dependencies

Error

Location: SKILL.md:42
Finding: Unpinned Third-Party MCP Package Is Downloaded and Executed
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:82
Finding: Local Images May Be Sent to an External Vision Service Without Explicit Disclosure or Confirmation
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
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

Findings (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The trigger conditions are extremely broad, matching nearly any mention of common image extensions or requests to review or describe an image. Overbroad activation increases the chance the skill will run in unintended contexts, causing unnecessary external data transmission or tool use on sensitive screenshots, mockups, or local file paths.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill description says it analyzes images using the MiniMax MCP tool but does not clearly warn that image files, URLs, or extracted contents may be sent to an external third-party service. This is a privacy and data-handling issue, especially for screenshots, documents, UI mockups, or local images that may contain credentials, personal data, or proprietary information.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 89% confidence
Finding: The skill instructs users to install and run an MCP server package via uvx minimax-coding-plan-mcp without pinning an exact version or digest. This creates a supply-chain risk: a future malicious or compromised release could be pulled automatically and granted access to image content, local files, or agent context through the MCP integration.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.