ClawHub
Back to skill

Security audit

find-package

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it says: help users find packages from pickup codes and shelf photos, without hidden or unrelated behavior.

Install only if you are comfortable sending pickup codes, app screenshots, and shelf photos through the configured Telegram/OpenClaw bot. Crop screenshots where possible and avoid including unrelated addresses, phone numbers, faces, or other people's packages.

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
92% confidence
Finding
The trigger guidance is broad enough to activate on common delivery-related phrases and even on a standalone pickup code in context, which increases the chance of unintended invocation. In an agent system, ambiguous triggers can route user messages and images into this skill without clear intent, causing unnecessary processing of package photos and pickup-code data.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.