ClawHub
Back to skill

Security audit

Scavio Google Ai Mode

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Scavio API helper that sends user queries to a third-party search-answer service, with no hidden execution or persistence found.

Install only if you are comfortable sending your search questions, and any optional region or location parameters you provide, to Scavio. Avoid using it for secrets, private personal details, or sensitive business queries unless Scavio's data handling terms fit your needs.

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
94% confidence
Finding
The skill sends user-supplied queries and optional locale/location data to Scavio's third-party API, but the description and setup do not clearly warn users about that external data sharing. This is a real privacy/transparency issue because users may disclose sensitive questions or location context without realizing the data leaves the local agent environment.

External Transmission

Medium
Category
Data Exfiltration
Content
import os, requests

response = requests.post(
    "https://api.scavio.dev/api/v2/google/ai-mode",
    headers={"Authorization": f"Bearer {os.environ['SCAVIO_API_KEY']}"},
    json={"query": "best running shoes for flat feet 2026", "gl": "us", "hl": "en"},
)
Confidence
86% confidence
Finding
https://api.scavio.dev/

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:35