Spend Tracker
Security checks across malware telemetry and agentic risk
Overview
This appears to be a coherent set of repo-specific ClawHub and Convex workflow skills with disclosed command/API use and guardrails around impactful actions.
Install this only if you want an agent to help operate or develop the ClawHub/Convex repo. Review commands before allowing authenticated GitHub, Convex, proof-publishing, or moderation actions, especially bans, role changes, unhide operations, and review helpers that may run with broad local access.
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.