ClawHub
Back to skill

Security audit

mini-token-remains

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward MiniMax quota checker that discloses its credential use and network call, with only minor trigger-word and language-scope caveats.

Install this only if you are comfortable with the agent reading your local MiniMax auth profile and sending a read-only quota request to MiniMax. Use explicit MiniMax wording when invoking it to avoid accidental activation for unrelated quota questions.

A.I.G

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

SkillSpector

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
95% confidence
Finding

The trigger phrases are generic account/quota questions that could easily appear in normal conversation, increasing the chance the skill activates unintentionally. That can cause unnecessary access to billing/usage data and may expose operational metadata to users who did not explicitly intend to invoke this skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

All user-facing instructions, trigger phrases, and output examples are written only in Chinese, with no indication that other languages are supported or that the user can choose a locale. This can be a natural-language policy issue when a skill implicitly enforces one language without opt-in or justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.