Security audit
Identyclaw A2a Trust Skill
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed trust-envelope helper for OpenClaw inter-agent messages, with expected credential use and no evidence of hidden execution or exfiltration.
Before installing, confirm you trust IdentyClaw and the required OpenClaw plugins, and review the missing local @rodit/hola-client dependency if you plan to run the npm helper scripts. Keep NEAR private keys and IDENTYCLAW_JWT scoped and protected, and do not let a verified envelope override normal task authorization, sandboxing, or approval checks.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.