futures-panda
Security checks across malware telemetry and agentic risk
Overview
The inspected skill content is coherent workflow guidance for ClawHub and Convex development, with high-impact actions disclosed and gated rather than hidden or automatic.
Install only if you want these repository-maintenance workflows. Review the sensitive commands before use, especially moderation, PR publishing, Convex deployment/proof runs, and the autoreview helper's full-access default; use the documented confirmation and opt-out controls 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
63/63 vendors flagged this skill as clean.