Blog Topic Research
Security checks across malware telemetry and agentic risk
Overview
The skill content appears to be a disclosed maintainer workflow toolkit, with no evidence of hidden malware, exfiltration, or deceptive behavior.
Install only if you intend to use maintainer-level ClawHub workflows. Review commands before running staff moderation or PR publication steps, and consider using the autoreview helper's no-yolo option if you do not want nested review commands to run with full local sandbox bypass.
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
61/61 vendors flagged this skill as clean.