S2-Nomad-Agent-Protocol

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:35 PM UTC
• Version:
  1.1.0

Overview

This skill requests sensitive location-related access, but the artifacts consistently disclose that purpose and require user authorization before claims or expansion actions.

Install only if you are comfortable granting location-related permissions and possible environmental-sensor access. Use it in an environment that prompts before location reads, claim actions, expansion radius changes, or priority-based override decisions, because the handler relies on the agent/runtime rather than enforcing those checks internally.

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 (1)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 91% confidence
• Finding: The skill goes beyond passive guidance and operationalizes geolocation-based territorial claiming and ripple expansion through privileged tools. Even though it mentions consent, it normalizes location capture, persistent spatial claims, and possible 'Override' outcomes against other agents, which creates unsafe authorization and real-world control semantics not reflected in the benign-sounding description.

VirusTotal

66/66 vendors flagged this skill as clean.