CAI: connect-polymarket-with-cai
Security checks across malware telemetry and agentic risk
Overview
This is a coherent developer workflow skill bundle whose powerful ClawHub, Convex, GitHub, and review commands are disclosed and mostly guarded by user-directed workflows.
Install this only in a trusted ClawHub or Convex development context. Before invoking moderation, publishing, remote validation, or autoreview flows, review the exact command and credentials involved; use the autoreview helper's --no-yolo option or AUTOREVIEW_YOLO=0 if you do not want nested Codex to run with full filesystem/sandbox bypass permissions.
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.