ClawHub
Back to skill

Security audit

主题声明锁定

Security checks for vulnerabilities and agentic risk

Overview

This is a writing-workflow skill that asks the agent to validate and record a story theme before drafting, with no hidden code execution or credential access found.

Install this if you want a strict Chinese-language story-planning checkpoint before pitch drafting. Be aware that it may slow or block creative drafting until the theme checks pass, and non-Chinese users may need translation or a bilingual version.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger list includes broad natural-language phrases such as '它相信什么' and '价值观锚点', which can plausibly appear in ordinary creative discussion and unintentionally activate this skill. Because the skill is a gatekeeper that blocks downstream creative steps until its checks pass, accidental invocation can alter workflow, constrain outputs, or cause denial-of-service-like friction in unrelated conversations.

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 content is written entirely in Chinese and does not offer user-language negotiation or an opt-in mechanism. In multilingual environments this can cause misunderstanding of constraints, failed verification steps, or silent workflow errors when users or downstream agents expect another language, making policy enforcement less reliable.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.