ClawHub

Product Management OS

Security checks across malware telemetry and agentic risk

Overview

This is a content-only product management playbook with broad activation language but no hidden code, credentials, persistence, or unsafe authority.

Install this if you want an agent to apply a broad PM operating-system framework. Be aware it may activate for ordinary product or planning requests, so prefer explicit `/pm ...` prompts when you want this skill and use a narrower skill when you need a more specialized workflow.

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
95% confidence
Finding
The README advertises a very broad natural-language trigger: "Help me create a product strategy for our new feature." This overlaps with ordinary user phrasing and could cause the skill to activate unintentionally in unrelated contexts where a user is simply asking for general help, expanding the skill's influence beyond explicit invocation. In a product-management skill, that creates prompt-routing and scope-control risk rather than direct code-execution risk.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill description is broadly scoped to many common product and planning activities, which can cause it to activate for routine requests that do not specifically require this skill. Overbroad activation increases the chance of unintended invocation, prompt-surface expansion, and interference with more appropriate or narrower skills, which is a real security and reliability concern even though the content itself is not overtly malicious.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal