tang poetry challenge
Security checks across malware telemetry and agentic risk
Overview
This appears to be a coherent ClawHub repository and CLI/tooling artifact with disclosed registry, moderation, telemetry, and development workflows rather than hidden or deceptive behavior.
Install or use this artifact only if you trust ClawHub/OpenClaw tooling with registry and developer workflow authority. Review the repo-local maintainer skills before enabling them in an agent environment, especially moderation commands, GitHub publishing/commenting workflows, and the autoreview helper's full-access mode.
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.