guandan
Security checks across malware telemetry and agentic risk
Overview
This skill is a transparent wrapper for a local GuanDan game CLI, with no evidence of hidden data access or unsafe behavior in the submitted files.
Install only if you are comfortable relying on the external npm package @mikewei-labs/clawguandan, since the submitted skill mainly delegates to that CLI. Review the CLI before enabling llm-bot mode or configuring any external model services.
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.