Security audit

Dataify Google News

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent Google News-to-Dataify API helper, with user confirmation before outbound calls, but users should handle the API token carefully.

Install only if you are comfortable sending Google News queries and selected parameters to Dataify. Store DATAIFY_API_TOKEN securely, avoid passing tokens on the command line when possible, and review the confirmation table before approving each API call.

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 (5)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 93% confidence
Finding: The skill instructs the agent to read environment variables for a token, read local reference files and scripts, and make external network/API calls, yet no declared permissions are present. This creates a capability/consent mismatch: the platform or reviewer may underestimate what the skill can access and transmit, increasing the risk of accidental secret exposure or unauthorized outbound requests.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The trigger phrases are broad enough to activate on ordinary conversation about news, which can cause the skill to run unexpectedly. In this skill, unexpected activation is more concerning because it can lead to token checks, parameter collection, file/script use, and eventual outbound API calls to a third party when the user may not have intended to invoke this integration.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger description is overly broad, matching common phrases like 'news search/information' and 'call Google News'. This can cause the skill to activate in unintended contexts, increasing the chance that user queries are routed to an external API without clear intent or with insufficient parameter review.

Vague Triggers

Low

Confidence: 86% confidence
Finding: The default prompt directs the agent to use the skill for a generic 'search query' without clearly constraining that it is specifically for Google News requests. Overly broad invocation guidance can cause the skill to trigger in unintended contexts, leading to unnecessary external data access or tool use beyond user intent.

Ssd 3

Medium

Confidence: 98% confidence
Finding: Passing a user-provided token on the command line can expose the credential through shell history, process listings, logs, debug output, or telemetry. In the context of an agent skill that may display commands or execute them in shared environments, this materially increases the risk of secret disclosure and downstream API account compromise.

VirusTotal

54/54 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:45

Instructions pass high-value credentials through process argv.

Critical

Code: suspicious.secret_argv_exposure
Location: SKILL.zh-CN.md:42