Security audit
zxz-test
Security checks across malware telemetry and agentic risk
Overview
The skills are mostly coherent for ClawHub and Convex maintenance, but they include default unrestricted nested review execution and staff moderation commands that deserve careful review before installation.
Install only in a trusted ClawHub maintainer environment. Prefer running autoreview with --no-yolo or AUTOREVIEW_YOLO=0 unless unrestricted nested review is truly needed, and check diffs for secrets before allowing fallback external reviewers. Use the moderation commands only with the intended staff account, explicit targets, and documented reasons.
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
62/62 vendors flagged this skill as clean.