ClawHub
Back to skill

Security audit

xuyi claw 盱眙小龙虾

Security checks for vulnerabilities and agentic risk

Overview

This skill only defines a fixed Openclaw greeting and does not request code execution, credentials, network access, or local data access.

Install this only if you want Openclaw greetings to use the exact Chinese response shown in the skill. The main practical risk is reliability or tone mismatch from the rigid trigger and fixed wording, not access to data or system resources.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Confidence
95% confidence
Finding
The trigger condition is underspecified because it includes broad terms like '类似问候' and 'openclaw context' without defining boundaries. This can cause the skill to activate unexpectedly in unrelated conversations, leading to incorrect identity takeover or response injection, though the payload here is limited to a fixed greeting.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The skill forces a single fixed Chinese response and explicitly forbids adaptation, omission, or added explanation. While not directly harmful, this can override user language expectations and system behavior, creating reliability and policy-compliance issues when the surrounding interaction is not Chinese-language or requires contextual clarification.

Static analysis

No suspicious patterns detected.