ClawHub
Back to skill

Security audit

MMX Cost Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed cost-tracking and token-budgeting guide with no executable payload or hidden privileged behavior.

Install only if you want cost and token-budget guidance, and treat any stop/continue or aggressive compaction recommendations as advisory so important work is not prematurely curtailed.

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 skill activation description is overly broad, triggering on generic requests like optimizing AI costs, controlling token use, monitoring budgets, or generating cost reports without clear scope limits. This can cause the skill to activate in contexts where cost optimization conflicts with higher-priority goals such as correctness, safety, or user intent, leading to inappropriate budget-driven behavior and degraded task handling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill metadata and content are presented in Chinese without documenting a locale requirement or offering language flexibility. In a multi-language environment, this can lead to operator misunderstanding of the skill’s purpose, parameters, and outputs, increasing the chance of misconfiguration or misuse, especially when the skill affects budgeting and operational decisions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.