Alvis GitHub CLI
Security checks across malware telemetry and agentic risk
Overview
The skills are mostly coherent repo-maintainer tools, but they include high-impact moderation and review automation that needs careful human control.
Install only in a trusted ClawHub maintainer environment with appropriate GitHub, Convex, and moderator credentials. Review commands before writes, prefer the documented confirmation flow, consider running autoreview with --no-yolo and disabling fallback reviewers when code confidentiality matters, and avoid using these skills in unrelated repositories or with broad personal credentials.
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
66/66 vendors flagged this skill as clean.