ClawHub
Back to skill

Security audit

Dataify Google Local

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Google Local-to-Dataify API helper that requires user confirmation before sending requests.

Install this only if you intend to send Google Local search parameters to Dataify and are comfortable providing a Dataify API token through the conversation or DATAIFY_API_TOKEN. Review the preview table before confirming any call, especially because the trigger wording may match generic local-search requests.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill invokes local scripts, reads reference files, accesses environment variables for tokens, and makes outbound requests, yet declares no permissions. That mismatch reduces transparency and can bypass policy or user expectations about what the skill is allowed to do, especially because it handles credentials and external network access.

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding
The public description frames this as a simple Google Local request transformer, but the skill also performs third-party API calls, token handling, parameter introspection, and broad natural-language parsing. This mismatch can cause users or orchestrators to invoke the skill without understanding that secrets may be processed and data will be sent to an external service.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger text includes broad phrases like 'call Google Local' and mentions of 'local search field,' which can match ordinary conversation and cause unintended activation. In context, unintended activation matters because the skill can collect parameters, prompt for credentials, and send requests to an external service.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger description is broad and ambiguous: phrases like 'call Google Local', 'local search', 'nearby search', and any mention of a local search field can match many ordinary user requests without clear boundaries. This can cause unintended skill activation, routing user input to an external API flow when the user did not explicitly intend that tool, increasing the risk of surprise data disclosure or incorrect tool use.

VirusTotal

65/65 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:65

Instructions pass high-value credentials through process argv.

Critical
Code
suspicious.secret_argv_exposure
Location
SKILL.zh-CN.md:65