Content Structure Frameworks
Security checks across malware telemetry and agentic risk
Overview
The inspected skill artifacts are coherent workflow helpers with disclosed repo, Convex, review, and moderation capabilities, and no evidence of hidden or malicious behavior.
Install only in the intended ClawHub/Convex maintenance context. Review commands before running staff moderation actions, keep admin/API credentials scoped, and use the autoreview helper's `--no-yolo` or `AUTOREVIEW_YOLO=0` option if you do not want nested Codex review to run with full access.
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
64/64 vendors flagged this skill as clean.