ClawHub
Back to skill

Security audit

memory-optimizer

Security checks across malware telemetry and agentic risk

Overview

This skill locally generates study plans and charts with disclosed command and file use, with no evidence of hidden network, credential, or destructive behavior.

Install this if you want a local study-plan generator that can run its bundled Node.js script. Be aware it may activate on general study or memory questions, and only provide an output path when you are comfortable creating or overwriting that Markdown report and SVG chart.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (4)

Context-Inappropriate Capability

Medium
Confidence
90% confidence
Finding
The skill grants and directs use of the exec tool even though its user-facing purpose is study-plan generation. Allowing shell execution for a content-planning skill unnecessarily expands the attack surface: user-controlled task data or file paths may later be passed into commands or scripts, enabling command abuse or execution of untrusted local code.

Context-Inappropriate Capability

Medium
Confidence
94% confidence
Finding
The workflow explicitly instructs the agent to run a Node.js command, operationalizing code execution as part of normal handling. In a skill that processes conversational user input, this creates a direct bridge from untrusted input to command execution and file creation, which becomes dangerous if argument construction, JSON handling, or output paths are not tightly constrained.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The auto-trigger rules are broad enough to activate on many ordinary study or memory questions, causing the skill to take over unexpectedly. Because the skill also supports execution and file output, overbroad triggering increases the chance that higher-risk actions occur without clear user intent or adequate consent.

Missing User Warnings

Low
Confidence
79% confidence
Finding
The skill permits writing a report and companion SVG file without clearly warning the user that files will be created on the filesystem. Silent or implicit file writes can surprise users, overwrite existing files, or leak sensitive study data into persistent storage, especially when output paths are user-influenced.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.