ClawHub

AI PM Agent

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed product-management planning skill that creates local markdown documents and shows no hidden code, credential use, network exfiltration, or destructive behavior.

Install this only if you want structured PM workflows that may create or update planning files in the current project. Before running it, choose an appropriate workspace and check whether DISCOVERY.md, PRD.md, EXPERIMENT.md, or GTM.md already exist so you can avoid unintended overwrites.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill metadata advertises very broad trigger phrases such as 'write PRD', 'competitor analysis', and 'product strategy', which are common user requests and can cause the skill to activate in situations where the user did not explicitly ask to run this workflow. Over-broad invocation increases the chance of unintended subagent execution and file generation, reducing user control and making prompt-routing mistakes more likely.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The example trigger 'I want to build [product idea]' is extremely generic and overlaps with ordinary brainstorming or advice-seeking requests. This makes accidental invocation likely, which can launch a multi-phase workflow and create artifacts even when the user only intended a lightweight discussion.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill writes several markdown files to the project root, but this side effect is not clearly surfaced up front in the description or usage guidance. Users may invoke the skill without realizing it will modify the workspace, which can create clutter, overwrite expectations, or interact poorly with existing repository workflows.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal