AIBase-News-Get

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:22 PM UTC
• Version:
  1.0.0

Overview

This is a straightforward AI news scraper that fetches public web pages and writes crawl results locally, with no evidence of deception, exfiltration, or unsafe persistence.

Install only if you want an agent to fetch AIBase news pages and store scraped article data locally. Run it from a directory where creating a News folder and replacing news_latest.json is acceptable, and choose an explicit output path if you need tighter control.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 88% confidence
• Finding: The skill documentation describes capabilities that include network access and local file read/write behavior, but it does not declare permissions or provide explicit permission boundaries. This is dangerous because agents or users may invoke the skill without understanding that it can access external sites and modify local files, increasing the chance of unintended data exposure or filesystem changes.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 92% confidence
• Finding: The documented purpose understates important behaviors: the skill writes crawl results to local storage, scans local Markdown files for deduplication, and claims summary generation without actually implementing it. This mismatch is dangerous because it can mislead users and orchestration systems about what data the skill touches and what actions it performs, undermining informed consent and safe policy decisions.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill says it writes output files and supports a force option, but it does not clearly warn users that files will be created locally and may be overwritten. This is risky because a user or agent may run it in a sensitive directory and unintentionally replace existing content or persist scraped data without realizing it.

VirusTotal

66/66 vendors flagged this skill as clean.