JWT Debugger
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill artifacts are purpose-aligned ClawHub and Convex workflow helpers with disclosed use of local tools, auth-gated moderation commands, and review/proof automation.
Install only if you want ClawHub/Convex maintainer workflow automation. Pay particular attention before using the moderation skill or the autoreview helper: moderation commands can affect users and public content, and autoreview defaults to an unsandboxed nested review mode unless run with its opt-out flag.
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.