ClawHub
Back to skill

Security audit

ImageKit

Security checks across malware telemetry and agentic risk

Overview

This appears to be a purpose-aligned ImageKit connector skill, with a broad trigger wording that users should interpret narrowly.

Install this only if you intend to let the agent help with ImageKit tasks. Treat broad ImageKit prompts carefully, and explicitly review any proposed upload, update, deletion, or account-changing action before approving it.

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
85% confidence
Finding
The skill declares it should be used for ANY ImageKit request, creating an unusually broad routing scope. In agentic environments, this can cause the skill to activate for loosely related prompts and funnel users into connector-mediated actions, increasing the chance of unintended data access or state-changing operations if the agent misinterprets intent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.