ClawHub
Back to skill

Security audit

Starwars

Security checks across malware telemetry and agentic risk

Overview

This is a small read-only Star Wars lookup skill that discloses its use of SWAPI and shows no hidden data access, persistence, or destructive behavior in the reviewed bundle.

Reasonable to install for ordinary Star Wars lookups. Be aware that using it may send lookup terms to swapi.dev, and inspect the external GitHub repository separately before following the optional manual clone, chmod, or /usr/local/bin symlink instructions.

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
87% confidence
Finding
The skill advertises broad natural-language phrases like "Look up Luke Skywalker" and "What planet is Tatooine?" as usage examples without defining strict trigger boundaries or requiring an explicit command form. In agent ecosystems, this can cause over-broad activation or unintended tool invocation from normal conversation text, which may lead to unnecessary external requests and tool use based on ambiguous user intent.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.