ClawHub
Back to skill

Security audit

招商行动指南

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language report generator for investment-attraction planning and does not show hidden, destructive, or privilege-seeking behavior.

Before installing, expect the skill to produce a Chinese investment-attraction action guide using public industry, policy, enterprise, and project information. Users should verify business claims and enterprise targets before acting on the report, especially because the skill itself notes that some conclusions may be inferential.

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

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instructions are written as a direct role and output specification entirely in Chinese, and the display name and report template consistently prescribe Chinese-language responses. There is no indication that the user may choose another language, which creates a language/locale policy issue under the rule for forced language without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.