ClawHub

Performance Profiler

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a local code performance analysis helper with no evidence of data theft, persistence, or unsafe system access.

Installers should expect a lightweight code performance review skill. Consider narrowing its triggers before broad deployment so ordinary requests containing 'performance' or '优化建议' do not invoke it unintentionally.

SkillSpector

By NVIDIA
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 (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger phrases include broad terms like "performance" and "优化建议", which are common in ordinary user requests and can cause the skill to activate outside its intended scope. Over-broad activation can route unrelated prompts into this skill, causing misfires, reduced reliability, and unintended handling of user data or tasks.

Natural-Language Policy Violations

Medium
Confidence
87% confidence
Finding
The description is written in Chinese and implicitly fixes the interaction/output language without indicating that the user's preferred language should be respected. This can create usability and policy issues by overriding user expectations, leading to incorrect or inaccessible responses rather than a direct security compromise.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger patterns are very broad and generic, including both Chinese and English terms like 'performance' and '优化建议', which can cause the skill to activate in many unrelated contexts. Over-broad activation increases the chance that code or sensitive content is routed into this skill unexpectedly, creating misclassification, unintended data exposure to the skill pipeline, and unreliable agent behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal