Gpt Tasteskill
Security checks across malware telemetry and agentic risk
Overview
The artifact is coherent and scans clean; its auth, network, publishing, and administration behavior is disclosed and fits a ClawHub registry/maintenance toolset.
Install or use this only if you intend to work with ClawHub development or registry operations. Treat stored CLI tokens and admin commands carefully, use dry-run and confirmation paths for moderation or email actions, and avoid running production-affecting commands unless you understand the target deployment.
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.