Back to skill

Security audit

MiniMax Coding Plan Tool Patched

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent MiniMax API wrapper for web search and image understanding, with expected external API and local-image upload behavior that users should understand before use.

Install only if you are comfortable sending search queries, prompts, image URLs, and any selected local image files to MiniMax using your API key. Avoid using sensitive, regulated, or confidential images or prompts unless that external transmission is acceptable for your use case.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill declares access to a sensitive environment variable (MINIMAX_API_KEY) but does not explicitly declare tool scope or permissions boundaries. This can mislead users and reviewers about what the skill can access, reducing transparency and making unintended secret exposure or unauthorized external API usage harder to detect.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill advertises web search and image understanding, including local file support, but does not warn that search queries, image contents, and potentially local file data are transmitted to the external MiniMax API. This creates a meaningful privacy and data-handling risk because users may provide sensitive prompts or images without realizing they leave the local environment.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The image analysis path accepts a local file path, reads the file, base64-encodes its contents, and sends it to a remote MiniMax API as image_url data. This creates a real data exfiltration risk because a user or calling agent may believe they are only analyzing a local image, while the tool silently transmits the full file contents off-host without an explicit warning or consent step.

Content

No source excerpt is available for this finding.