Inversion Protocol
Security checks across malware telemetry and agentic risk
Overview
The skills are coherent ClawHub maintenance tools, but one review helper gives a nested AI reviewer broad unsandboxed access by default.
Install only if you are comfortable with ClawHub maintainer workflows and with the autoreview helper's default full-access nested reviewer. Prefer running it with --no-yolo or AUTOREVIEW_YOLO=0 unless you specifically want that level of authority, and use moderation or PR publishing commands only with explicit targets and credentials you intend to use.
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.