ClawHub
Back to skill

Security audit

Dataify Google Patents

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Google Patents API helper that requires user confirmation before sending searches and does not show evidence of hidden or destructive behavior.

Install this only if you intend to send patent-search queries and filters to Dataify's Scraper API. Review the confirmation table before approving a call, and provide a Dataify API token only when you trust the workspace and need the request to run.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
85% confidence
Finding
The skill instructs the agent to read local reference files, access environment-provided API tokens, and make outbound network requests, but no permissions are explicitly declared. That mismatch weakens reviewability and enforcement, because users and platform controls may not have clear visibility into the skill's actual capabilities before execution.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger condition is overly broad because it activates not only on explicit requests to call Google Patents, but also when the user merely mentions the patent search field. This can cause the skill to engage in contexts where the user did not intend an external API action, increasing the chance of unintended parameter collection, confirmation prompts, or eventual network calls involving sensitive query content.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.secret_argv_exposure

Instructions pass high-value credentials through process argv.

Critical
Code
suspicious.secret_argv_exposure
Location
SKILL.md:68

Instructions pass high-value credentials through process argv.

Critical
Code
suspicious.secret_argv_exposure
Location
SKILL.zh-CN.md:69