Agent Rule Pilot
Security checks across malware telemetry and agentic risk
Overview
The skill artifacts are coherent developer and maintainer workflows with disclosed command, auth, and moderation authority.
Install only in a development or maintainer context where you are comfortable allowing the agent to run repo tools, GitHub/Convex commands, and ClawHub moderation workflows. Review the autoreview full-access default and use its no-yolo option if you want normal sandbox prompts.
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.