ClawHub
Back to skill

Security audit

image-prompt

Security checks across malware telemetry and agentic risk

Overview

This is a non-executable image-planning skill that is coherent with its stated social-post visual briefing and routing purpose.

Before installing, note that this skill may activate for broad image or graphic requests; it is intended as a planning and routing aid for social-post visuals, not as a generator itself.

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 (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The invocation examples include broad phrases such as "make a graphic" and "what image should I use," which can occur in ordinary conversation and are not tightly scoped to this specific skill. The description also mixes explicit phrases with a vague condition ("is unsure which image tool/model to use"), making activation boundaries less clear.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.