ClawHub
Back to skill

Security audit

小河狸发票助手

Security checks for vulnerabilities and agentic risk

Overview

This ClawHub entry is a placeholder that points users to official external sources and contains no executable skill implementation.

This ClawHub package itself is only a pointer. Before installing or using the external full version, review the official source, install instructions, and license terms, especially because the artifact says the official version uses a non-resale license rather than the platform default license label.

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 (1)

Natural-Language Policy Violations

Low
Confidence
86% confidence
Finding
The markdown explicitly labels the recommended official channel as being for Chinese users only, which introduces a language/locale preference in user-facing guidance. There is no accompanying opt-in choice or explanation that the skill itself is region-specific, so this can be read as a locale constraint without documented justification.

Static analysis

No suspicious patterns detected.