ClawHub
Back to skill

Security audit

AI印刷设计师

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese print-design guidance skill with no executable code, network behavior, persistence, or credential access.

Installers should expect this skill to answer in Chinese and focus on print-production design. Consider narrowing activation phrases if accidental routing from general design requests would be disruptive.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list includes broad everyday phrases such as '帮我设计' and '设计版面', which can match many unrelated user requests and cause the skill to activate outside its intended print-production context. Over-broad invocation increases the risk of incorrect routing, unintended instruction precedence, and user confusion, especially in environments where skills can influence system behavior automatically.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill is effectively Chinese-only and does not offer language negotiation or clearly limit itself to Chinese-speaking users. In multilingual deployments, this can cause misrouting, misunderstood safety-relevant print specifications, and degraded user comprehension, especially for technical parameters like bleed, color mode, or export settings.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.