ClawHub
Back to skill

Security audit

Robotaxi Briefing

Security checks across malware telemetry and agentic risk

Overview

This skill is a public-news briefing workflow with narrowly scoped local report storage and no evidence of hidden credential use or broad system access.

Install if you want an agent to fetch public robotaxi-sector news and store briefing history in OpenClaw memory. Be aware that it instructs cleanup of robotaxi_report_*.md files older than 24 hours, so keep separate copies if you need long-term audit or comparison history, and do not provide credentials unless a future version clearly explains why they are needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs automatic deletion of prior report files older than 24 hours, but provides no user-facing warning, confirmation, or scope guard beyond a filename glob. Even though the target path is narrow, this is still destructive behavior embedded in normal execution and can cause unintended data loss if reports are needed for audit, debugging, or historical comparison.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.