OpenClaw Zulip Channel
Security checks across malware telemetry and agentic risk
Overview
This looks like a coherent set of ClawHub and Convex workflow skills with powerful but disclosed developer and staff commands.
Install only in a trusted ClawHub/Convex repo context. Use least-privilege GitHub, ClawHub, and Convex credentials; review moderation commands before approving them; and for sensitive code, consider disabling autoreview full-access mode or external fallback reviewers.
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
63/63 vendors flagged this skill as clean.