Security audit
Ai Information Science
Security checks across malware telemetry and agentic risk
Overview
The skill package is coherent and disclosed, with high-impact admin and migration workflows guarded by explicit dry-run, target, reason, and confirmation requirements.
Install only if you trust the operators and repository context for ClawHub/Convex work. Before using the staff or migration skills, confirm the target, deployment, command, and dry-run output, because approved actions can affect production users, emails, packages, or data.
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.