A2a Protocol

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a normal Agent2Agent protocol client that sends user-directed messages and tasks to remote agent endpoints.

Install only if you intend to send prompts, task data, or agent messages to the configured remote A2A endpoint. Avoid sending secrets or sensitive files unless you trust the endpoint and understand how it stores or processes requests.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill advertises sending messages and tasks to remote agents and supporting API keys/Bearer tokens, yet it provides no warning that user content may leave the local environment and be processed by third parties. In an agent ecosystem, this is especially risky because prompts, task data, secrets, or sensitive outputs could be forwarded to untrusted remote endpoints with little user awareness.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal