Dataify Bing News

• Outcome: Review
• Latest audit: Jul 16, 2026 · 8:45 PM UTC
• Version: 1.2.0

Overview

This is a disclosed Dataify Bing News helper that needs an API token and sends confirmed search terms to Dataify, with credential-handling cautions but no hidden or destructive behavior found.

Use this skill only if you are comfortable providing a Dataify API token and sending your news search terms to Dataify/ScraperAPI. Prefer a dedicated environment variable or explicit token parameter, avoid putting unrelated secrets or confidential text in search prompts, and review raw API output before sharing it elsewhere.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 91% confidence
• Finding: The skill instructs the agent to read an API token from the environment and perform external network calls, but the skill metadata does not declare those capabilities or permissions. Undeclared access to secrets and outbound requests weakens reviewability and consent boundaries, increasing the risk of accidental secret use or data exfiltration through the invoked script.

Context-Inappropriate Capability

Medium

• Confidence: 95% confidence
• Finding: The skill extracts API tokens from natural-language prompt text and then persists the resolved token into the process environment. This creates an unnecessary secret-handling path for a news search skill, increases the chance of prompt-supplied secret exfiltration, and broadens token exposure to other code running in the same process.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The documentation explicitly instructs making live API calls using user-provided search terms but does not warn that those queries will be transmitted to an external third-party service. This creates a real privacy and data-handling risk because users or downstream agents may send sensitive, regulated, or proprietary text off-platform without informed consent or filtering.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The code scans free-form user prompt text for token-like values and treats them as API credentials without a clear, explicit consent boundary at the call site. This can cause users or upstream agents to accidentally disclose secrets in ordinary text and have them silently used for outbound authentication.

Ssd 3

Medium

• Confidence: 95% confidence
• Finding: The skill explicitly instructs the agent to return script/API output directly without review, summarization, or redaction. If the script or upstream API echoes sensitive values such as user-supplied tokens, query details, internal errors, or other confidential data, the agent could disclose them back to the user or into logs unchanged.

Env Variable Harvesting

High

• Category: Data Exfiltration

Content

token = token.strip()
    if not token.lower().startswith("bearer "):
        token = f"Bearer {token}"
    os.environ["DATAIFY_API_TOKEN"] = token
    return token

• Confidence: 97% confidence
• Finding: os.environ["DATAIFY_API_TOKEN"]

VirusTotal

65/65 vendors flagged this skill as clean.

Static analysis

Detected: suspicious.secret_argv_exposure

Instructions pass high-value credentials through process argv.

Critical

• Code: suspicious.secret_argv_exposure
• Location: SKILL.zh-CN.md:36