skill-test-demo

• Outcome: Pass
• Latest audit: Jun 15, 2026 at 8:33 AM UTC
• Version:
  1.0.0

Overview

This skill is a disclosed ZingAPI query helper that uses expected credentials and network access for its stated advertising-creative search purpose.

Install only if you intend to let the agent query ZingAPI with your ZingAPI credentials. Keep the access key secret out of chat/log output, review any raw JSON request body before sending it, and use dry-run when you want to inspect the signed request without making the API call.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• 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)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 90% confidence
• Finding: The skill instructs use of environment-based credentials, local file inputs such as `@request.json`, and outbound network access, but the skill manifest shown does not declare any permissions or capability boundaries. This creates a transparency and governance gap: an agent may read local files, access secrets, and send requests externally without an explicit permission contract, increasing the risk of unintended data exposure or over-privileged execution.

VirusTotal

64/64 vendors flagged this skill as clean.