Security audit
Agent Token Cost Signal Kit
Security checks across malware telemetry and agentic risk
Overview
This skill is a read-only guide for evaluating agent token cost and does not show hidden execution, credential collection, or destructive behavior.
Safe to install for agent cost-evaluation help. Redact sensitive logs before pasting them, and use the global or force install commands only if you intend the skill to affect the wider OpenClaw installation.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.