ClawHub

Marketing Strategy Pmm

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only product marketing planning skill; it gives broad launch and outreach advice but does not install code, request access, or automate actions.

Safe to install as a planning/reference skill. Treat its generated marketing plans as drafts: verify claims and market data, add privacy/legal review before outreach or tracking, and require explicit human approval before using any separate tools to send emails, publish posts, change ad budgets, update CRM records, or contact customers.

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
89% confidence
Finding
The trigger list contains several generic business phrases such as "PMM," "positioning," "go-to-market," and "competitive analysis" that are likely to appear in ordinary conversations. This can cause the skill to activate unintentionally, exposing users to irrelevant guidance, overriding more appropriate skills, or broadening the attack surface if downstream skill execution has elevated capabilities.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The checklist directs teams to run email blasts, in-app announcements, paid ads, HubSpot campaign tracking, UTMs, attribution, webinar registration, and VIP customer outreach, but it provides no privacy, consent, or compliance guardrails. In a PMM skill, these steps are likely business-standard rather than malicious, but omitting consent checks, lawful-basis review, unsubscribe handling, and regional compliance can lead users to conduct outreach and tracking in ways that violate privacy requirements or internal policy.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal