Security audit

Dataify Google Finance

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Google Finance lookup wrapper for Dataify and does not show evidence of hidden, destructive, or unrelated behavior.

Use this skill only when you intend to query Google Finance through Dataify. Expect your query parameters and Dataify API token to be sent to scraperapi.dataify.com after you confirm the preview table; avoid pasting tokens unless you trust the environment.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
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
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 88% confidence
Finding: The skill invokes local Python scripts, reads reference files, accesses environment variables for API tokens, and performs network requests, but it declares no permissions or equivalent capability boundaries. This creates a trust and review gap: users and platforms may not realize the skill can access secrets and exfiltrate data over the network, increasing the risk of unintended token disclosure or unauthorized external calls.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The trigger condition includes any request that 'explicitly mentions something related to financial data,' which is broad enough to capture many unrelated or sensitive conversations about investments, funds, currencies, or futures. Over-broad activation can route user data to this skill unexpectedly and cause external API preparation or prompting in contexts where the user did not intend to use Google Finance.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger condition includes very broad finance-related language, so ordinary conversations about stocks, currencies, or funds could invoke this skill even when the user did not intend to call an external scraping/API workflow. In this context, over-triggering is meaningful because the skill can lead to token handling and outbound requests, increasing the chance of unintended external data access or accidental disclosure of user intent to a third-party service.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill instructs the agent to send a user-supplied Dataify token in an outbound Authorization header but does not require warning or explicit confirmation that a credential will be transmitted to a third-party service. This creates a credential-handling risk because users may not realize their token is being sent externally, and the instruction to hide Authorization from the pre-call confirmation table further reduces transparency.

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:64

Instructions pass high-value credentials through process argv.

Critical

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