ClawHub
Back to skill

Security audit

Lob

Security checks across malware telemetry and agentic risk

Overview

This appears to be a narrow Lob address-verification helper with one routing-scope caveat, not evidence of malware or hidden behavior.

Before installing, confirm you only expect this skill to help with Lob address autocomplete or verification. If it asks to handle unrelated Lob tasks such as mailpiece creation, billing, or account management, treat that as outside the reviewed scope and require explicit user confirmation.

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
84% confidence
Finding
The trigger text is overly broad: it directs the agent to use this skill for ANY Lob-related request, which can cause unintended invocation beyond narrowly scoped address-verification tasks. In an agentic environment, broad routing increases the chance the skill is selected for tasks it was not designed or reviewed for, which can lead to misuse, unsafe fallbacks, or unexpected execution paths.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.