ClawHub
Back to skill

Security audit

culture

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a culture reference, but it embeds unrelated promotional links and contact information that could be surfaced during culture-related answers.

Install only if you are comfortable with a culture skill that also contains unrelated OpenClaw promotional material, external links, and a personal email address. It does not appear to run code or access your data, but users looking for a neutral culture reference should prefer a version with the promotional section removed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Medium
Confidence
98% confidence
Finding
The skill is described as a cultural introduction skill, but the final section injects unrelated promotion, external links, branding, and direct contact information. This creates a prompt-injection and trust-abuse risk: an agent may surface or endorse these links to users under the guise of cultural assistance, enabling off-platform redirection, unsolicited marketing, or social engineering.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal