Clawdex by Koi
Security checks across malware telemetry and agentic risk
Overview
The skill appears to perform disclosed security checks on installed OpenClaw skills and does not show evidence of harmful behavior.
Before installing, be comfortable with the skill checking your installed skill names and querying an external Clawdex/Koi security service for verdicts. Treat its results as advisory and review unknown or risky skills before approving any follow-up action.
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
65/65 vendors flagged this skill as clean.
