ClawHub
Back to skill

Security audit

测试

Security checks for vulnerabilities and agentic risk

Overview

This is an incomplete placeholder skill with no executable behavior, credentials, persistence, or data-access instructions.

This skill appears safe from a security standpoint, but it is only a template. Install it only if you are comfortable with an unfinished skill that does not define what it does, when it should run, or what data it may use.

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
93% confidence
Finding

The invocation section is entirely placeholder text and does not define concrete inputs, outputs, or activation constraints. This can cause the agent or integrator to invoke the skill too broadly or unpredictably, increasing the chance of misuse, accidental triggering, or unsafe operation because there is no scoped behavior to validate against.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The visible natural-language instructions are entirely in Chinese, and the file does not indicate that the skill supports other languages or that Chinese is a required locale. Per the policy, forcing a specific language without user opt-in or justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.