auto-novel-writer
Security checks across malware telemetry and agentic risk
Overview
The reviewed materials are coherent ClawHub development and moderation guidance, with no artifact-backed evidence of hidden or malicious behavior.
Install only if you are a ClawHub maintainer or developer who expects these workflows. Use the moderation and GitHub publishing commands only with the intended authenticated accounts, explicit targets, and confirmation for state-changing actions.
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
65/65 vendors flagged this skill as clean.