Stop Burning Tokens — OpenClaw Cost Diagnostic Primer
Security checks across malware telemetry and agentic risk
Overview
The available scan inputs are clean and the inspected skill artifacts do not show hidden, destructive, or purpose-mismatched behavior.
Install only if you want these repository-maintenance workflows available to your agent. Review any command before letting it run against production services, GitHub, Convex, or moderation targets, and keep normal secret-handling practices in place.
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
VirusTotal findings are pending for this skill version.