Security audit

Dataify Google Play

Security checks across malware telemetry and agentic risk

Overview

This skill coherently performs confirmed Google Play lookups through Dataify and does not show hidden, destructive, or persistent behavior.

Install only if you are comfortable using Dataify as the intermediary for Google Play searches. Keep the Dataify token scoped and private, review the confirmation table before approving calls, and avoid entering sensitive queries because confirmed requests are sent to Dataify.

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
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (4)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 91% confidence
Finding: The skill invokes local Python scripts, reads tokens from environment variables or CLI input, accesses bundled reference files, and makes authenticated network requests to a third-party API, yet no permissions are declared. This creates a transparency and governance gap: users or platform controls may not understand that the skill can access credentials and exfiltrate request data off-platform.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 94% confidence
Finding: The stated description suggests a narrow Google Play search/ranking helper, but the skill actually supports broad scraping operations, token-based pagination, device/category browsing, cache bypass, and authenticated calls to Dataify. This mismatch can cause unsafe auto-triggering and under-informed consent, increasing the chance that users send data or credentials to an external service without realizing the full scope of behavior.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: Trigger phrases like 'call Google Play' and 'app store search/ranking' are broad and ambiguous, which can cause the skill to activate in contexts where the user did not intend a third-party scraping/API call. Because the skill can lead to authenticated network requests, overbroad activation increases the risk of unintended data disclosure and confusing handoff to an external service.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The reference instructs the skill to send user-provided queries and an API bearer token to a third-party endpoint, but it does not mention this data flow, obtain consent, or warn about privacy implications. In an agent skill context, users may assume they are querying Google Play directly, when in fact their prompts and the credentialed request are sent to Dataify, creating transparency and data-handling risk.

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:58

Instructions pass high-value credentials through process argv.

Critical

Code: suspicious.secret_argv_exposure
Location: SKILL.zh-CN.md:59