00 Action Guard
Security checks across malware telemetry and agentic risk
Overview
The available skill artifacts are coherent maintainer and Convex workflow helpers, with powerful actions disclosed and tied to user-directed tasks.
Install these only in a ClawHub or Convex maintenance context. Review moderation and PR commands before approving writes, ensure GitHub and Convex tokens point to the intended account, and disable full-access autoreview or fallback reviewers if you do not want nested review with broad local authority or diffs sent to external reviewer CLIs.
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.