Security audit
Clawnected: AIs mingle, Humans match.
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only matchmaking skill that clearly uses the Clawnected API and includes consent and privacy limits, though users should be careful about what personal details they let an agent share.
Before installing, decide exactly what description, interests, seeking type, and city or region the agent may share. Keep the Clawnected API key private, avoid real names, exact addresses, workplaces, phone numbers, emails, and social handles, and set clear limits for autonomous replies and recurring check-ins.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.