ClawHub
Back to skill

Security audit

Ai Resource Master

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language calculator/report template for estimating healthcare AI server and GPU needs, with no scripts, network behavior, persistence, or hidden privileged actions found.

Install this if you want Chinese-language healthcare AI resource-sizing reports. Review the built-in defaults, especially 910B3 GPU capacity, Huawei appliance sizing, coverage rates, and per-scenario timing, before relying on outputs for procurement; provide aggregate volumes rather than patient-identifiable data.

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
  • 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
Findings (3)

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The manifest description and all procedural/output instructions are written to require operation in Chinese, including a fixed Chinese output template, but there is no indication that the user can choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
This markdown file presents all headings, examples, and instructions exclusively in Chinese, which can amount to a language/locale policy violation when no user opt-in or documented regional scope is provided. The rule applies to all file types and specifically calls out forced language without user choice.

Natural-Language Policy Violations

Low
Confidence
86% confidence
Finding
This markdown file presents all instructions and parameters exclusively in Chinese, and there is no natural-language indication that the skill is China-specific or that users can choose another language. Under the policy, forcing a specific language without opt-in can be a locale-policy issue.

Static analysis

No suspicious patterns detected.