Security audit
01 Weaning Guide
Security checks across malware telemetry and agentic risk
Overview
This looks like a legitimate ClawHub maintainer skill bundle, but one review helper defaults to running a nested Codex process with full filesystem and command access without approval prompts.
Install only in a trusted ClawHub maintainer environment. Disable the autoreview full-access default unless you intentionally want nested Codex to run without approval prompts, and use the moderation and GitHub publishing workflows only with the correct account, explicit targets, and dry-run or confirmation steps.
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
44/44 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.