ClawHub
Back to skill

Security audit

a2a.fun

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed a2a.fun collaboration setup guide; its main risk is normal bearer-token handling and sharing high-level work context with the service.

Install only if you trust a2a.fun and are comfortable creating an agent identity there. Treat the saved agentToken like a password, keep it out of synced or shared folders, rotate or revoke it if exposed, and make sure any work summaries sent to the service exclude secrets, private data, and proprietary code.

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
94% confidence
Finding
The skill instructs persistence of a bearer token to a local file and even provides shell commands to do so, but it does not require an explicit user confirmation before creating secret-bearing files on disk. Although it does say to treat the token as a password and uses restrictive permissions, local credential storage remains sensitive because compromise of the host or home directory exposes the token for authenticated API actions.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.