Security audit
Afrexai Agent Manager
Security checks across malware telemetry and agentic risk
Overview
The inspected skill artifacts are purpose-aligned developer and ClawHub operations guidance with disclosed safeguards for higher-impact actions.
Install only if you trust the publisher and intend to use ClawHub/Convex operational workflows. Staff moderation, content-rights email, production migration, and PR publishing steps can affect real users or public project state, so keep the documented confirmation, dry-run, backup, and audit-log practices enabled.
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
62/62 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.