ClawHub
Back to skill

Security audit

Google Chat

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Google Chat connector whose main risk is that it can act as the connected user to read, send, edit, delete, react to messages, and move attachments.

Install this only for agents that should operate Google Chat as your connected account. Treat message creation, updates, deletes, reactions, and attachment uploads/downloads as user-visible actions; confirm the target space/message/file before allowing them, especially when deleting messages or moving sensitive attachments.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (4)

Missing User Warnings

Medium
Confidence
79% confidence
Finding
The skill exposes destructive and state-changing actions such as `create_message`, `reply_message`, `update_message`, `delete_message`, `add_reaction`, and `delete_reaction` without clear cautions or confirmation guidance. In an agent context, this increases the risk of accidental data loss, unwanted communications, or unauthorized workflow side effects if a prompt or upstream task causes the agent to invoke these actions without adequate user awareness.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The skill exposes message deletion as a direct action without any documented warning, confirmation, or guardrails for destructive use. In an agentic context, this increases the risk of accidental or prompt-induced irreversible deletion of user or team communications.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
Downloading chat attachments into File Manager copies potentially sensitive chat data into persistent storage, changing its exposure and retention properties. Without a warning or retention guidance, an agent may exfiltrate or retain files beyond the user’s expectations.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
Standalone upload of File Manager content into Chat enables transmission of stored files into collaboration spaces, which can disclose sensitive data if invoked mistakenly or via prompt manipulation. The absence of warning or consent guidance makes this more dangerous in an agent environment that can bridge storage and messaging systems.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.