bilibili-hot
Security checks across malware telemetry and agentic risk
Overview
The inspected skill artifacts are transparent ClawHub and Convex development helpers; they include powerful commands, but the behavior is disclosed and tied to user-directed workflows.
Install only if you want repo-local ClawHub/Convex workflow assistance. Be especially careful with the moderation and autoreview helpers: confirm the target repo/account, review commands before write actions, and use the no-yolo option for autoreview if you do not want nested Codex full-access execution.
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.