Financial Modeling Prep
Security checks across malware telemetry and agentic risk
Overview
The packaged skills describe disclosed developer, Convex, ClawHub moderation, and review workflows with no artifact evidence of hidden exfiltration, destructive automation, or deceptive behavior.
Install only if you want Codex to assist with ClawHub/Convex maintainer workflows. Review the moderation and autoreview skills before use: moderation commands can ban users or change roles, and the autoreview helper may run nested review with broad local authority unless invoked with its safer opt-out option.
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
63/63 vendors flagged this skill as clean.