ClawHub

sjsjsjsms

Security checks across malware telemetry and agentic risk

Overview

This is a non-executable AI product-management coaching skill with broad triggers but no evidence of hidden access, credential use, persistence, or destructive behavior.

Reasonable to install for AI product-design coaching. Be aware that generic phrases like “AI 产品”, “产品设计”, “PRD”, or “继续” may invoke it in ordinary PM discussions, and do not paste confidential product plans, customer data, credentials, or regulated business details unless your workspace policy allows that.

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger terms in the description are very broad, covering common phrases like 'AI 产品', '产品设计', and 'PRD' that can appear in many normal conversations. In a subagent runtime, this increases the chance of unintended invocation, causing the skill to intercept unrelated discussions and potentially influence user flows or chain internal skill calls without clear user intent.

Vague Triggers

Low
Confidence
88% confidence
Finding
The continuation example uses a generic phrase like '继续', which is highly ambiguous outside an already-established skill session. If the platform uses such examples for routing or continuation heuristics, the skill may reactivate during unrelated conversations, leading to unintended context capture and workflow steering.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal