Security audit

MiniMax Vision Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small MiniMax vision helper with disclosed setup and usage steps, though users should handle the CLI install and API key carefully.

Install mmx-cli only if you trust the npm package source, avoid using sudo, and consider pinning a reviewed version. Do not paste API keys into shared terminals, logs, scripts, or source control; rotate the key if it may have been exposed.

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

Warning

Location: SKILL.md:12
Finding: Unpinned Global npm Dependency Installation
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:32
Finding: API Key Passed Through Command-Line Arguments
Content: View full analysis
``` ``` The prerequisite section also presents the same pattern: ```markdown - Authenticated: `mmx auth login --api-key ` ``` ### Technical Analysis The instructions encourage users to replace the placeholder with a real MiniMax API key directly in a shell command. Command-line arguments can be recorded in interactive shell history and may be collected by terminal logging, diagnostics, audit tooling, or command telemetry. On systems where process arguments are visible to other users or monitoring services, the key may also be exposed while the command is running. Although no actual credential is hardcoded in the project, the documented credential-handling method creates a realistic disclosure risk. ### Attack Path 1. A user replaces `` with a valid MiniMax API key. 2. The user executes the command in an interactive shell. 3. The complete command is retained in shell history, captured by logging or diagnostic tooling, or temporarily exposed through process metadata. 4. Another local user, support bundle recipient, log reader, backup recipient, or attacker with access to the history file retrieves the key. 5. The attacker uses the exposed key to authenticate to MiniMax and consume the victim's authorized API resources. ### Impact Assessment Exposure could allow unauthorized use of the affected MiniMax account's API privileges, including consumption of paid quota and access to operations permitted by the key. The precise scope depends on the privileges assigned to the exposed ke ...[truncated 145 chars]
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.