ClawHub
Back to skill

Security audit

ai-code-optimizer

Security checks across malware telemetry and agentic risk

Overview

This is a simple code-optimization skill with disclosed code-editing behavior and no hidden installer or executable components.

Install only if you want an agent to analyze and potentially change code files. Review before/after output and diffs carefully, especially for production, security-sensitive, authentication, cryptographic, or large codebases.

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 (3)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger examples are broad enough to match ordinary coding-assistance requests, which can cause the skill to activate unexpectedly during normal conversations. That increases the chance of unintentional file analysis or modification behavior being invoked without the user clearly opting into this specific skill.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill promises to apply improvements automatically but does not warn that it may modify code, which creates a risk of silent or unexpected changes to user files. In a coding assistant context, automatic modification without explicit confirmation can introduce integrity, availability, and security issues if changes are applied incorrectly or to the wrong target.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill description promises to 'automatically optimize code' for multiple goals without defining scope, supported languages, safety boundaries, or required user confirmation. In an agent setting, overly broad activation criteria can cause the skill to engage on sensitive code or make unintended refactors, increasing the risk of unsafe changes, policy bypass, or modification of security-relevant logic.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.