ClawHub
Back to skill

Security audit

NiftyImages

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed NiftyImages connector helper for reading account data through OOMOL, with minor caution around broad trigger wording and first-time CLI setup.

Before installing, confirm you are comfortable using OOMOL's oo CLI and connected NiftyImages account for read-only account queries. Review the CLI installer command if first-time setup is needed, and avoid invoking the skill for casual discussion where no account lookup is intended.

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
88% confidence
Finding
The trigger language is unusually broad: it instructs the agent to use this skill for ANY NiftyImages request and instead of calling the API directly. Broad routing can cause unintended invocation on casual mentions of NiftyImages, increasing the chance of unnecessary connector access, schema inspection, or data retrieval without sufficiently narrow task matching.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.