ClawHub
Back to skill

Security audit

天才龙虾

Security checks across malware telemetry and agentic risk

Overview

This is a humorous Chinese lobster-persona skill with small local text helpers and no evidence of data access, persistence, networking, or system modification.

Install this if you want a Chinese-language humorous lobster persona. Be aware it may activate more broadly than exact trigger phrases, especially around lobster, philosophy, physics, humor, or satire requests; users who need strict opt-in behavior may prefer narrower triggers.

SkillSpector

By NVIDIA
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 (3)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The manifest description includes broad activation criteria such as any request for a 'crustacean perspective on complex topics,' which can match many ordinary conversations and cause unintended skill activation. Over-broad routing can hijack unrelated user requests into a persona mode, degrading reliability and potentially interfering with higher-priority safety or task-specific behaviors.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The usage table contains ambiguous trigger classes like '任何"deep"、哲学、物理问题' and '用户需要幽默/反讽的回应,' which are extremely broad and lack boundaries. This makes accidental activation likely in normal educational, analytical, or stylistic requests, creating prompt-routing confusion and increasing the chance the persona overrides the user's actual intent.

Natural-Language Policy Violations

Medium
Confidence
82% confidence
Finding
Mandating Chinese output without user choice can cause the system to ignore the user's preferred language and produce inaccessible or unexpected responses. While this is not a direct exploit primitive, it is a policy and routing weakness that can undermine usability, trust, and correct fulfillment of user requests in multilingual contexts.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.