Security audit

a2a-Market-ACP-Lite-Negotiation

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed gateway negotiation CLI; its network calls, optional model use, local command spawning, and long polling are aligned with that purpose.

Use this with a trusted gateway, especially if changing the default localhost URL. Replace the default auth token for real deployments, avoid passing real API keys directly on the command line when possible, use a trusted OpenClaw executable if enabling the OpenClaw decision engine, and set max-polls or stop-on-session-end if you want bounded operation.

SkillSpector

By NVIDIA

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec, suspicious.env_credential_access

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: src/cli/index.js:572

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: src/cli/index.js:497