ClawHub
Back to skill

Security audit

Ship Learn Next

Security checks across malware telemetry and agentic risk

Overview

This appears to be a planning skill whose main risk is that it may create plan files more eagerly than some users expect.

Install if you want an agent to turn notes or goals into saved planning documents. Review the generated file path and ask the agent to show plans inline first if you do not want extra files created automatically.

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
91% confidence
Finding
The activation conditions are broad and include generic phrases like wanting to 'turn this into a plan' or 'make this actionable,' which can cause the skill to trigger in contexts the user did not explicitly intend. In an agent environment, unintended invocation can lead to inappropriate steering of the conversation and chaining into later behaviors such as file creation without sufficiently clear consent.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to always save a plan to a file and present it as completed, but it does not require obtaining explicit user consent before creating or modifying files. In agentic systems, automatic file writes are a meaningful side effect that can clutter workspaces, overwrite user expectations, or be combined with unintended activation to produce unauthorized artifacts.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.