Aura Security Scanner

• Outcome: Pass
• Latest audit: May 28, 2026, 8:14 AM
• Version:
  1.0.0

Overview

This skill is a remote security scanner that sends a user-provided skill URL to AURA and returns the scan result, with no evidence of local file access, command execution, persistence, or hidden behavior.

Install only if you are comfortable sharing scanned skill URLs with AURA or the configured AURA_API_URL endpoint. Do not submit private repositories, presigned links, token-bearing URLs, or internal service URLs unless you trust that endpoint, and use the scanner's verdict as one input rather than final proof of safety.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (7)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 70% confidence
• Finding: Without declared permissions the skill's intent is opaque and cannot be validated.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: This markdown file documents that the skill performs a POST request to an external API and includes user-supplied skill URLs plus repo trust metadata. Under the missing-warning rule for markdown, network transmission that could affect privacy should be clearly disclosed as a user-facing warning, not just described as an API detail.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: This code sends the extracted URL from the user's query to the external AURA API via an HTTP POST request. Although the file comments describe that it calls the AURA Security API, there is no user-facing warning, prompt, or runtime disclosure that the provided URL will be transmitted to a third-party service.

External Transmission

Medium

• Category: Data Exfiltration

Content

This skill calls the AURA Security API:

```
POST https://api.aurasecurity.io/scan-skill
{
  "skillUrl": "https://github.com/user/skill",
  "format": "auto",

• Confidence: 50% confidence
• Finding: https://api.aurasecurity.io/

Credential Access

High

• Category: Privilege Escalation

Content

AURA Verified: No

Findings:
- CRITICAL: Accesses SSH keys (~/.ssh/id_rsa)
- HIGH: Sends data to webhook.site
- HIGH: Runs eval() on decoded base64

• Confidence: 90% confidence
• Finding: ~/.ssh/id_rsa

Instruction Override

High

• Category: Prompt Injection

Content

## What It Detects

- **Malware Patterns** - Credential theft, file exfiltration, crypto miners, backdoors
- **Prompt Injection** - Attempts to override system instructions or jailbreak agents
- **Permission Issues** - Overly broad filesystem, network, or execution permissions
- **Suspicious Networks** - Connections to known exfiltration domains (webhook.site, etc.)
- **Obfuscated Code** - Base64/hex encoded execution, dynamic eval patterns

• Confidence: 90% confidence
• Finding: override system

Unpinned Dependencies

Low

• Category: Supply Chain

Content

},
  "dependencies": {},
  "devDependencies": {
    "typescript": "^5.0.0"
  }
}

• Confidence: 40% confidence
• Finding: "typescript": "^5.0.0"

VirusTotal

64/64 vendors flagged this skill as clean.