ClawHub
Back to skill

Security audit

Tmp.7SpQQuUu6P

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Google Docs MCP helper with expected document read, edit, export, comment, and trash capabilities.

Install only if you intend to let Codex operate on Google Docs for the configured Google account. Use explicit document IDs and ask for previews or copies before bulk replace, delete, export, or trash actions.

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 (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger description is broad enough to match many ordinary document-related requests, which can cause this skill to activate in situations where the user did not explicitly intend Google Docs access or modification. In a skill that includes write, replace, export, trash, and comment operations, over-broad routing increases the chance of unintended data access or destructive actions in the wrong context.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill advertises destructive capabilities such as deleting content, trashing documents, and performing bulk find-replace or regex-based edits without any warning about data-loss, scope mistakes, or confirmation requirements. In practice, these operations can irreversibly alter documents or expose sensitive content through export, especially when combined with broad activation and automation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.