OpenClaw Hot Skills

Security checks across malware telemetry and agentic risk

Overview

This skill is a ClawHub marketplace discovery helper, and its behavior is disclosed, scoped to searching/ranking skills, and gated before installation.

Install this only if you want ClawHub skill-discovery assistance and are comfortable trusting the `clawhub` CLI dependency. Expect it to contact ClawHub for rankings and check which skills are installed locally; review any recommended skill separately before confirming installation.

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
83% confidence
Finding
The skill advertises very broad trigger phrases like general requests for finding a skill or extending capabilities, which can cause it to activate in situations beyond its intended scope. That increases the chance the agent invokes external tooling unexpectedly, performs network-backed discovery, or steers the conversation toward installation workflows the user did not explicitly request.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal