ClickHouse GitHub Forensics
Security checks across malware telemetry and agentic risk
Overview
The skill bundle is mostly coherent for ClawHub maintainer work, but one review helper defaults to running nested Codex with full filesystem authority and approvals bypassed.
Install only if you trust this as a ClawHub maintainer toolkit. Review the `autoreview` helper before use, and prefer `--no-yolo` or disabling automatic review/test execution when you do not want nested tools to run with full filesystem access. Use the moderation and PR-maintainer workflows only with the intended ClawHub credentials and explicit targets.
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.