ClawHub
Back to skill

Security audit

Tmp.Mcm9LVMTCP

Security checks across malware telemetry and agentic risk

Overview

This skill is read-only and mostly transparent, but it routes broad hiking requests through a signed-in AllTrails browser session and can read personal AllTrails account data.

Install only if you are comfortable giving an unofficial, reverse-engineered AllTrails integration read access through your signed-in browser tab. Use it for personal AllTrails tasks, avoid bulk extraction, and be aware it may run for generic hiking/trail prompts unless your agent lets you constrain skill use.

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
89% confidence
Finding
The trigger description is broad enough to match many generic hiking- or trail-related queries, which can cause the skill to activate when the user did not explicitly intend to use this unofficial AllTrails integration. In this case, unintended invocation is more concerning because the skill can access signed-in user data and relies on a reverse-engineered browser-bridge flow, increasing privacy and compliance risk if invoked unnecessarily.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.