ClawHub
Back to skill

Security audit

Pm Review

Security checks across malware telemetry and agentic risk

Overview

This is a coherent product/page review skill, with the main caution that it may use external web or image tools when reviewing URLs and screenshots.

Install this if you want PM/product-style review of webpages or design screenshots. Be careful with sensitive material: avoid submitting private screenshots, internal-only URLs, logged-in pages, customer data, credentials, or confidential product plans unless you trust the configured web and image-analysis tools and understand where they send the data.

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 (1)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill’s trigger description is broad and overlaps with many common requests such as ‘分析截图’, ‘评估设计’, and ‘界面分析’, which can cause the agent to invoke this skill when the user did not intend a PM-style review. Mis-triggering is dangerous because the skill is authorized to fetch external URLs and analyze user-provided files, expanding data exposure and causing the agent to follow the wrong workflow on unrelated tasks.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.