ClawHub
Back to skill

Security audit

Google Messages Local Archive

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed, read-only playbook for searching a user's local Google Messages archive, with appropriate warnings around sensitive message data.

Install only if you are comfortable giving gmcli and your agent read access to your local Google Messages archive. Keep the workflow read-only unless you separately decide to use gmcli's write-capable features, and review the external gmcli project because the skill depends on that CLI for authentication, storage, and message access.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.prompt_injection_instructions

Prompt-injection style instruction pattern detected.

Warn
Code
suspicious.prompt_injection_instructions
Location
SKILL.md:199