ClawHub
Back to skill

Security audit

A Share Glossary Tutor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese-language A-share investing glossary helper that discloses a narrow local note-writing behavior.

Before installing, expect the skill to maintain a local glossary at notes/stocks/glossary.md. Avoid pasting private account details or sensitive financial context if you do not want that material included in notes.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs automatic appending to a local file (notes/stocks/glossary.md) without any explicit user consent, preview, or warning that local data will be modified. Even though the target is a notes file and the content is educational, silent persistence can create unwanted local side effects, leak sensitive pasted context into storage, or be abused to accumulate untrusted content over time.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description includes 中文优先, which indicates a language preference imposed by the skill. There is no corresponding statement offering the user a language choice or making the locale preference optional.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.