ClawHub
Back to skill

Security audit

Copywriting

Security checks for vulnerabilities and agentic risk

Overview

This is a simple copywriting prompt skill with no executable code, persistence, credentials, or external access.

This skill is safe to install as a prompt-only copywriting helper. Users should still provide only text they are comfortable having rewritten by their agent, and should explicitly request Chinese or English output when language matters.

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
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest description includes '中英文切换' as a built-in behavior, but the file does not state that the user chooses the language or that the skill preserves the user's current language by default. Because language/locale policy applies to all file types, this can be read as an implicit language-selection behavior without explicit opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.