Security audit
Finance Knowledge Base
Security checks across malware telemetry and agentic risk
Overview
The skill artifacts are coherent developer and maintainer workflows with disclosed commands and no evidence of hidden or malicious behavior.
Install only if you want these repository-specific ClawHub and Convex workflows. Review the moderation and autoreview sections before use: they can affect accounts, public content, PRs, deployments, and local files when invoked, so use them with explicit targets and keep the documented confirmation and opt-out controls in place.
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.
Static analysis
No suspicious patterns detected.