ClawHub
Back to skill

Security audit

product-manager

Security checks across malware telemetry and agentic risk

Overview

This is a text-only product management assistant skill with no code execution, persistence, credentials, or hidden data movement.

Safe to install as a product planning and strategy assistant. Only provide business metrics, user feedback, analytics, or competitive information that is appropriate for the task, and treat its recommendations as advisory rather than automatic decisions.

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 invocation behavior is broadly defined as 'when invoked' followed by generic product-management actions, without clear trigger boundaries, authorization checks, or scope constraints. In an agentic system, this can cause the skill to activate in unintended contexts, query sensitive context sources, or influence decisions beyond the user's explicit request.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.