Security audit
抖音
Security checks across malware telemetry and agentic risk
Overview
The skills are mostly coherent development and moderation helpers, but the autoreview helper defaults to running nested Codex with full-access sandbox bypass, which is broad enough to require Review before installation.
Install only if you trust this publisher and understand the maintainer workflows. Before using `autoreview`, prefer running it with `--no-yolo` or set `AUTOREVIEW_YOLO=0`, and review any ClawHub moderation, PR publishing, Convex deployment, or proof-publishing command before allowing it to use your credentials or modify remote state.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.