Security audit
dotnet-core-expert
Security checks across malware telemetry and agentic risk
Overview
The skill set is mostly coherent for ClawHub and Convex maintenance, but one review helper grants broad full-access authority by default and may hand code diffs to fallback AI tools.
Install only if you trust the ClawHub maintainer workflow and understand the privileged commands. Before using `autoreview`, consider running it with `--no-yolo`, `AUTOREVIEW_YOLO=0`, and `--fallback-reviewer none` for sensitive repositories. Use moderation and proof-publishing commands only with the intended authenticated account and after checking the exact target and effect.
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.