Generate Legal Services Ad Creative Brief
Security checks across malware telemetry and agentic risk
Overview
The skill artifacts are coherent developer and maintainer workflow helpers with disclosed command use and no evidence of hidden data theft or destructive behavior outside their stated purpose.
This appears reasonable to install for ClawHub/Convex development work. Before using the autoreview helper, note that its default nested Codex review runs with broad local access unless you opt out with --no-yolo or AUTOREVIEW_YOLO=0. Use moderation and PR-maintainer workflows only with the intended authenticated ClawHub/GitHub accounts because they can make real account, content, or PR changes.
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.