Unanswered Messages
Security checks across malware telemetry and agentic risk
Overview
The artifacts form a coherent ClawHub maintainer and Convex workflow skill set with disclosed command use and no evidence of hidden persistence, exfiltration, or deceptive behavior.
Install only if you are comfortable with maintainer-grade workflows that may use your local repo, GitHub CLI auth, Convex credentials, and moderation APIs. Review exact commands before high-impact actions, use dry-run modes where available, and use --no-yolo for autoreview if you do not want nested Codex review to run with full-access sandbox bypass.
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.