Bilibili Helper
Security checks across malware telemetry and agentic risk
Overview
This skill appears safe for its intended maintainer/developer use, but it can run powerful moderation, GitHub, Convex, and review commands under your account.
Install only in a ClawHub/Convex maintainer environment where you trust the publisher and are comfortable letting the agent use your existing CLI credentials. Review commands before writes, prefer dry-run modes, and use the autoreview no-yolo option if you do not want nested full-access Codex review.
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
65/65 vendors flagged this skill as clean.