Phy Openclaw Multibot Audit
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-style security audit skill for OpenClaw Telegram bots, with no evidence of hidden execution, exfiltration, or unsafe persistence.
Install this as an audit aid for bot repositories you intend to review. Its snippets may inspect or help modify local bot configuration, and some examples discuss sensitive auth/profile files, so run remediation steps deliberately and review changes before deploying.
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
No VirusTotal findings