Security audit
Nlp Api Hub
Security checks across malware telemetry and agentic risk
Overview
The skill bundle is coherent and disclosed, with guarded maintainer workflows rather than hidden or deceptive behavior.
Install this only in a maintainer or developer context where ClawHub admin actions, Convex operations, and external code review tools are appropriate. Before using it, be aware that review workflows may transmit code diffs to configured model providers, and moderation/email/migration workflows should be run only with explicit user confirmation and the intended authenticated account.
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
53/53 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.