Parallel Agents
Security checks across malware telemetry and agentic risk
Overview
This is a coherent set of ClawHub maintainer and Convex development skills with powerful but disclosed workflows.
Install only if you are comfortable giving these skills maintainer-level access to the ClawHub repo and related accounts. Review moderation commands before confirming writes, avoid sending sensitive diffs to fallback reviewer CLIs unless approved, and use the documented --no-yolo or AUTOREVIEW_YOLO=0 option if you do not want full-access nested review.
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.