Oraclaw Graph
Security checks across malware telemetry and agentic risk
Overview
The skill artifacts are coherent with ClawHub and Convex development workflows, with sensitive moderation commands disclosed and bounded by user confirmation, auth, reasons, and audit logging.
Install only if you want these repo-specific ClawHub and Convex workflows. Treat the moderation skill as powerful: confirm the exact target and reason before any ban, unban, role change, report triage, or skill unhide action, and verify the result afterward.
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.