个人理财预算规划助手
Security checks across malware telemetry and agentic risk
Overview
The skill bundle is coherent and purpose-aligned, with sensitive commands disclosed and generally guarded by user direction, confirmation, or verification steps.
Install only if you want agent assistance with ClawHub maintainer workflows or Convex development. Before using it, be aware that moderation commands can affect public skills and user accounts, proof publishing can post artifacts/comments to GitHub, and the autoreview helper can run nested review with broad local access unless configured otherwise.
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.