ClawHub
Back to skill

Security audit

计量检测合规护栏

Security checks for vulnerabilities and agentic risk

Overview

This is a static Chinese metrology-compliance review skill with no executable code, persistence, credential use, or hidden data handling.

Install this only if you want Chinese metrology-compliance review behavior. Users should make clear when a document is unrelated to metrology so the skill is not applied too broadly, and they should verify legal or regulatory conclusions with qualified compliance staff before relying on them.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest description is entirely in Chinese and the skill output format and operating instructions are specified only in Chinese, implying a fixed language behavior. The file does not offer the user a language choice or explicitly justify the restriction as a locale-specific requirement, which fits the language/locale policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger conditions are broad enough to activate on generic review, publication, or generation requests for several common document categories, which can cause the skill to engage outside a narrowly scoped metrology-compliance workflow. In a guardrail skill, overbroad activation can lead to inappropriate interception, irrelevant policy application, or unintended influence over unrelated document handling, reducing reliability and increasing the chance of incorrect compliance blocking.

Content

No source excerpt is available for this finding.