Slo Calculator
Security checks across malware telemetry and agentic risk
Overview
The skills are mostly operational guidance for ClawHub and Convex workflows, with sensitive actions disclosed and generally tied to explicit user-driven tasks.
Install only if you want agent assistance with ClawHub maintainer/moderation and Convex development workflows. Review the commands before approving them, use the moderation and GitHub actions only with the right account permissions, and consider running the autoreview helper with --no-yolo if you do not want nested Codex review to bypass sandbox approvals.
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
65/65 vendors flagged this skill as clean.