Security audit
Hcc Meta Ai
Security checks across malware telemetry and agentic risk
Overview
This is a coherent set of developer and ClawHub operations skills with powerful but disclosed, user-gated workflows.
Use these skills only in the intended maintainer or admin context. Before running commands with --yes, --apply, --send, or production Convex targets, verify the target, reason, dry-run output, and credentials are correct.
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.