ClawHub

spots

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Google Places CLI helper, with expected but sensitive setup around a Google API key.

Before installing, verify the GitHub repository and consider pinning a known version instead of using @latest. Use a Google API key restricted to Places and Geocoding, set quotas or billing alerts, and avoid publishing exact secret-manager paths or exposing the key outside intentional CLI use.

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 (2)

Missing User Warnings

Medium
Confidence
81% confidence
Finding
The skill instructs users to configure a Google Places API key but does not include any guidance on safe handling, scoping, billing exposure, or privacy implications of using location/search data. In an agent-skill context, this omission increases the chance that users will paste high-privilege credentials into insecure environments or use unrestricted keys that can be abused if exposed.

Ssd 3

Medium
Confidence
93% confidence
Finding
The document discloses a concrete 1Password secret path for the Google API key, which reveals where a sensitive credential is stored and how it is named. Even without the secret value itself, this materially lowers the effort for an insider, compromised agent, or social-engineering attacker to target the exact vault item and can facilitate credential theft or misuse.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal