ClawHub
Back to skill

Security audit

Prompt Optimizer

Security checks across malware telemetry and agentic risk

Overview

This is a prompt-only answer-optimization skill with no code execution, data access, persistence, or hidden privileged behavior.

Installers should understand that this skill may influence answer structure whenever a request is ambiguous, and Chinese phrasing may shape outputs unless the user or system clearly specifies another language. It is otherwise a low-risk prompt-only skill.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill description is broad enough to match many ordinary, underspecified user requests, which can cause the skill to activate unexpectedly and steer conversations beyond the user’s intent. In a prompt-driven skill, overbroad activation increases the chance of instruction shadowing, unnecessary transformation of user input, and interference with safer or more specific system behaviors.

Natural-Language Policy Violations

Medium
Confidence
81% confidence
Finding
The skill is defined in Chinese and describes behavior/output in Chinese without offering language negotiation, which can override or conflict with the user’s requested language. This is dangerous mainly because it can degrade reliability, cause policy or instruction mismatch in multilingual contexts, and unexpectedly alter downstream content handling rather than because it directly enables code execution or data exfiltration.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.