ClawHub
Back to skill

Security audit

IceCube Service Pricing

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent pricing and payment template, but it asks agents to keep persistent customer and payment-status records without privacy or retention limits.

Review this skill before installing if you do not want agents to steer generic pricing or payment conversations into this specific IceCube service workflow. If used, keep customer names, amounts, and receivables out of shared or synced memory unless you have consent, access controls, and a deletion process; do not store payment credentials or full account details in the memory file.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger description uses very broad keywords like '服务报价', '定价', '收欟', and '报价单', which can cause the skill to activate during ordinary conversations unrelated to this billing workflow. Over-broad invocation increases the chance that users are steered into payment, quoting, or data-collection flows unexpectedly, which is risky for a skill centered on commercial transactions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description is written as a Chinese-only service workflow and does not indicate that users may interact in other languages or opt into Chinese output. Under the stated policy, forcing a specific language without user choice is a natural-language policy concern unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill instructs tracking customer names, project status, income, and outstanding payments in a memory file without any privacy, retention, access-control, or minimization guidance. This creates a realistic risk of exposing sensitive commercial and personal data, especially if the memory store is shared, synced, or insufficiently protected.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.