Self Preserve
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill artifacts are administrative and development helpers whose higher-impact actions are disclosed and tied to clear user-directed workflows.
Install only if you intend to use ClawHub maintainer or Convex development workflows. Treat the moderation and autoreview helpers as powerful: confirm targets before staff actions, keep API tokens protected, and use the autoreview no-yolo option if you do not want nested review with broad local sandbox authority.
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.