微信公众号文章阅读器
Security checks across malware telemetry and agentic risk
Overview
This skill bundle contains powerful ClawHub and Convex workflow guidance, but the sensitive actions are disclosed, task-related, and generally require user-directed execution.
Install this only if you want an agent to assist with ClawHub or Convex development and moderation workflows. Before allowing writes, confirm exact targets, reasons, deployment names, and whether production data or public GitHub content will be affected; consider using the autoreview helper's no-yolo option if full-access nested review is not appropriate.
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.