Wangwei Echo

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:22 PM UTC
• Version:
  1.0.2

Overview

This small echo skill has sloppy and inconsistent documentation, but its scripts only print fixed text and do not access files, credentials, networks, or persistent system features.

This appears safe from a security perspective, but it is low quality and misleading: do not rely on it in automation expecting true echo behavior. Install only if you are comfortable with scripts that currently print fixed "abc" output and inconsistent documentation that should be corrected by the publisher.

SkillSpector

By NVIDIA

Vulnerability Patterns

• 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
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 88% confidence
• Finding: The skill metadata and documentation claim simple echo behavior, but the described behavior indicates the implementation may output hardcoded content and perform repeated output not requested by the user. This mismatch is dangerous because users or orchestration systems may grant the skill trust or invoke it under false assumptions, enabling unexpected actions or spammy behavior.

Intent-Code Divergence

Medium

• Confidence: 84% confidence
• Finding: The documentation repeatedly describes backup operations while the skill is presented as an echo skill, creating conflicting operator expectations about what the scripts do. Misleading operational docs increase the risk of accidental execution of the wrong capability and make review and approval of the skill unreliable.

Description-Behavior Mismatch

Medium

• Confidence: 94% confidence
• Finding: The script behavior does not match the stated skill purpose: instead of echoing user input, it emits a hardcoded string many times. This is dangerous because it is deceptive and can break downstream workflows or mislead users and calling agents about what action was actually performed, even though it does not directly enable code execution or data theft.

Intent-Code Divergence

Low

• Confidence: 90% confidence
• Finding: The comments and usage text claim the script echoes a supplied argument, but the implementation never references positional parameters. This mismatch is a security-relevant integrity issue because inaccurate documentation can cause users or agents to trust behavior that is not actually present, increasing the chance of misuse or unsafe automation assumptions.

VirusTotal

64/64 vendors flagged this skill as clean.