Freeport
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill artifacts are disclosed workflow guidance and helper tooling for ClawHub and Convex development, with no evidence of hidden or malicious behavior.
Before installing, be aware that these skills are meant for maintainers and developers with repo and service access. Use the moderation and publish workflows only with the intended ClawHub credentials, and consider disabling autoreview full-access mode with its documented opt-out if you do not want nested review commands to run with broad local permissions.
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.