Funnlp
Security checks across malware telemetry and agentic risk
Overview
The skill artifacts are coherent developer and maintainer workflows with sensitive actions disclosed and guarded, though users should review the high-privilege review and moderation commands before use.
Install only if you expect ClawHub/Convex maintainer tooling. Review commands before allowing moderation writes, PR publishing, production Convex operations, or the autoreview helper's default full-access nested Codex review mode; use the documented opt-outs where appropriate.
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.
