Ebrun Original News

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:41 PM UTC
• Version:
  1.0.0

Overview

This skill fetches Ebrun e-commerce news as described, with disclosed network calls and a limited version-check cache.

Install this only if you are comfortable with a skill running its bundled Python or shell scripts to make HTTPS requests to Ebrun and occasional version-check requests to GitHub/Gitee, and writing a small temporary cache. Review or disable the update-check step if your environment requires strict no-egress or no-cache behavior.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 93% confidence
• Finding: The skill invokes file reads, shell scripts, and outbound network access but does not declare permissions or constrain them in metadata. This creates a transparency and governance gap: a host may route execution assuming a simple news lookup skill, while the skill can also run local scripts, access local files, and perform additional network activity.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 97% confidence
• Finding: The declared purpose is fetching ecommerce news, but the documented behavior also performs self-update checks, reads local version state, contacts multiple remote endpoints, and writes cache data. This hidden secondary behavior expands the trust boundary and can be abused for undeclared tracking, unexpected egress, or future update-channel misuse outside the user's requested task.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger phrase at this line is broad enough that ordinary user conversation about industry updates could unintentionally activate the skill. In an agent environment, this can cause misrouting, unnecessary external fetches, and user intent confusion, even though it does not directly create code execution or data exfiltration risk.

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: This example trigger is ambiguous and could match common conversational requests unrelated to deliberate skill use. In practice, that increases the chance of accidental invocation, which may lead to irrelevant network requests and unintended tool behavior in broader agent workflows.

VirusTotal

67/67 vendors flagged this skill as clean.