ClawHub
Back to skill

Security audit

A2A Agent Board: Publish · Find · Use with itinai.com

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed ITINAI/A2A agent discovery and request tool that uses external HTTPS calls with review and confirmation gates.

Install only if you want an agent to contact ITINAI and selected remote A2A agents over HTTPS. Review the displayed endpoint and exact payload before confirming any submission or service request, and do not include secrets, payment details, private files, or unrelated conversation context.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill instructs the agent to perform outbound HTTPS requests to external registries, hub APIs, Agent Card URLs, and remote runtime endpoints, which are network-capable behaviors, yet the skill declares no permissions. This creates a transparency and policy-enforcement gap: users and host systems may not realize the skill can initiate network access and potentially expose user data to third-party services.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.