Verified Research Engine (Web + Academic + Confidence Score)

• Outcome: Pass
• Latest audit: May 28, 2026, 10:48 AM
• Version:
  1.0.1

Overview

This is a coherent hosted search skill, but users should know their queries, prompts, URLs, and AIsa API key are sent to an external API.

Install only if you are comfortable sending search terms, research prompts, optional system instructions, and target URLs to AIsa and its upstream providers. Use a dedicated revocable API key, avoid secrets or confidential internal URLs, and be especially careful with Tavily crawl/map and Sonar Deep Research because they may process broader or more detailed content.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (17)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 94% confidence
• Finding: The skill declares required environment variables and clearly relies on network access, but it does not present an explicit permissions model or user-facing disclosure that it will send prompts, queries, and URLs to a third-party API. That creates a real transparency and consent gap: agents may invoke it with sensitive user data under the assumption it is just a local search helper.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 90% confidence
• Finding: The top-level description frames the skill as intelligent search, but the documented behavior also includes URL extraction, crawling, site mapping, explanation generation, multi-source aggregation, and arbitrary system-prompt injection into Sonar requests. This broader behavior materially changes the risk profile because it can fetch and process third-party content beyond a simple search query, increasing privacy, prompt-injection, and unintended data-transmission exposure.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The markdown instructs users to send arbitrary queries, message content, and URLs to external APIs but provides no privacy warning, data-sharing notice, or guidance against sending secrets, internal URLs, or regulated data. In a search skill, this omission is significant because users may naturally paste sensitive research topics, customer data, or private links into these requests.

Missing User Warnings

Medium

• Confidence: 84% confidence
• Finding: This client transmits user-provided queries and URLs to external third-party APIs, which can expose sensitive prompts, internal URLs, or proprietary research targets if callers assume processing is local. In an agent skill context, hidden external transmission increases privacy and data-governance risk because agents may pass user or workspace-derived content without clear consent or policy checks.

External Transmission

Medium

• Category: Data Exfiltration

Content

### Sonar

```bash
curl -X POST "https://api.aisa.one/apis/v1/perplexity/sonar" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

• Confidence: 86% confidence
• Finding: curl -X POST "https://api.aisa.one/apis/v1/perplexity/sonar" \ -H "Authorization: Bearer $AISA_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "sonar", "messages": [

External Transmission

Medium

• Category: Data Exfiltration

Content

### Web Search

```bash
curl -X POST "https://api.aisa.one/apis/v1/scholar/search/web?query=AI+frameworks&max_num_results=10" \
  -H "Authorization: Bearer $AISA_API_KEY"
```

• Confidence: 84% confidence
• Finding: https://api.aisa.one/

External Transmission

Medium

• Category: Data Exfiltration

Content

### Scholar Search

```bash
curl -X POST "https://api.aisa.one/apis/v1/scholar/search/scholar?query=transformer+models&max_num_results=10" \
  -H "Authorization: Bearer $AISA_API_KEY"

curl -X POST "https://api.aisa.one/apis/v1/scholar/search/scholar?query=LLM&max_num_results=10&as_ylo=2024&as_yhi=2025" \

• Confidence: 84% confidence
• Finding: https://api.aisa.one/

External Transmission

Medium

• Category: Data Exfiltration

Content

curl -X POST "https://api.aisa.one/apis/v1/scholar/search/scholar?query=transformer+models&max_num_results=10" \
  -H "Authorization: Bearer $AISA_API_KEY"

curl -X POST "https://api.aisa.one/apis/v1/scholar/search/scholar?query=LLM&max_num_results=10&as_ylo=2024&as_yhi=2025" \
  -H "Authorization: Bearer $AISA_API_KEY"
```

• Confidence: 84% confidence
• Finding: https://api.aisa.one/

External Transmission

Medium

• Category: Data Exfiltration

Content

### Hybrid Scholar Search

```bash
curl -X POST "https://api.aisa.one/apis/v1/scholar/search/smart?query=machine+learning+optimization&max_num_results=10" \
  -H "Authorization: Bearer $AISA_API_KEY"
```

• Confidence: 84% confidence
• Finding: https://api.aisa.one/

External Transmission

Medium

• Category: Data Exfiltration

Content

### Sonar

```bash
curl -X POST "https://api.aisa.one/apis/v1/perplexity/sonar" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

• Confidence: 86% confidence
• Finding: https://api.aisa.one/

External Transmission

Medium

• Category: Data Exfiltration

Content

### Sonar Pro

```bash
curl -X POST "https://api.aisa.one/apis/v1/perplexity/sonar-pro" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

• Confidence: 87% confidence
• Finding: https://api.aisa.one/

External Transmission

Medium

• Category: Data Exfiltration

Content

### Sonar Reasoning Pro

```bash
curl -X POST "https://api.aisa.one/apis/v1/perplexity/sonar-reasoning-pro" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

• Confidence: 87% confidence
• Finding: https://api.aisa.one/

External Transmission

Medium

• Category: Data Exfiltration

Content

### Sonar Deep Research

```bash
curl -X POST "https://api.aisa.one/apis/v1/perplexity/sonar-deep-research" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

• Confidence: 88% confidence
• Finding: https://api.aisa.one/

External Transmission

Medium

• Category: Data Exfiltration

Content

## Tavily APIs

```bash
curl -X POST "https://api.aisa.one/apis/v1/tavily/search" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query":"latest AI developments"}'

• Confidence: 85% confidence
• Finding: https://api.aisa.one/

External Transmission

Medium

• Category: Data Exfiltration

Content

-H "Content-Type: application/json" \
  -d '{"query":"latest AI developments"}'

curl -X POST "https://api.aisa.one/apis/v1/tavily/extract" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"urls":["https://example.com/article"]}'

• Confidence: 92% confidence
• Finding: https://api.aisa.one/

External Transmission

Medium

• Category: Data Exfiltration

Content

-H "Content-Type: application/json" \
  -d '{"urls":["https://example.com/article"]}'

curl -X POST "https://api.aisa.one/apis/v1/tavily/crawl" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.com","max_depth":2}'

• Confidence: 94% confidence
• Finding: https://api.aisa.one/

External Transmission

Medium

• Category: Data Exfiltration

Content

-H "Content-Type: application/json" \
  -d '{"url":"https://example.com","max_depth":2}'

curl -X POST "https://api.aisa.one/apis/v1/tavily/map" \
  -H "Authorization: Bearer $AISA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.com"}'

• Confidence: 92% confidence
• Finding: https://api.aisa.one/

VirusTotal

65/65 vendors flagged this skill as clean.