Security audit
Doc Orchestrator
Security checks across malware telemetry and agentic risk
Overview
The skill files describe repo maintenance, Convex development, review, UI proof, and moderation workflows with disclosed commands and guardrails; I did not find hidden exfiltration or deceptive behavior.
Install only if you want an agent to help with ClawHub/Convex development and maintenance. Review the high-impact workflows before use: moderation commands can ban users or change roles, GitHub commands can comment or close items, proof tooling can publish artifacts, and autoreview may launch a nested full-access Codex review unless configured otherwise.
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.