Security audit
找数据
Security checks across malware telemetry and agentic risk
Overview
The artifacts reviewed describe developer and ClawHub workflow helpers whose sensitive actions are disclosed and user-directed.
Install only if you want an agent to help with ClawHub maintainer and Convex developer workflows. Review before invoking actions that ban/unban users, change roles, comment on PRs, publish proof artifacts, run package setup, or start nested review commands with elevated sandbox settings.
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.
Static analysis
No suspicious patterns detected.