ClawHub
Back to skill

Security audit

AIsa Multi Search Engine

Security checks across malware telemetry and agentic risk

Overview

This is a coherent external search plugin that sends user queries and URLs to AIsa-backed search services, with no evidence of hidden local access, persistence, or destructive behavior.

Install only if you are comfortable sending search terms, research topics, supplied URLs, and extracted page content to AIsa and its integrated providers. Avoid secrets, internal-only URLs, regulated data, or confidential research unless your policy allows that external processing, and use a scoped AIsa API key.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill requires an API key and documents outbound calls to remote AIsa endpoints, but the manifest does not explicitly declare permissions despite exercising environment-variable access and network connectivity. This weakens user consent and reviewability because operators may not realize the skill can read secrets and transmit user queries and retrieved content off-platform.

Description-Behavior Mismatch

Medium
Confidence
81% confidence
Finding
The documented API reference advertises crawling and site-map generation endpoints that go beyond the stated search and extraction scope of the skill. Even if not exposed as current tools, this creates scope ambiguity and increases the risk of future overreach, misleading users and reviewers about what the skill may do with external sites.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill encourages users to submit search queries and URLs and to extract page content, but it does not clearly warn that this information will be transmitted to AIsa-operated endpoints and third-party-backed search providers such as Tavily and Perplexity. This creates a privacy and data-handling risk, especially if users provide sensitive prompts, private URLs, or regulated content.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The tool sends user-supplied search queries and URL lists to a third-party service (AIsa/Tavily/Perplexity) over the network, but the code provides no explicit disclosure, consent flow, or data-minimization guardrails. In a search plugin this is expected behavior, but it is still a real privacy/security issue because users may unknowingly transmit sensitive prompts, internal URLs, or proprietary research targets to external providers.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.