Security audit
ZM 选题策略与内容审核
Security checks across malware telemetry and agentic risk
Overview
The supplied telemetry and scans are clean, but I could not identify a packaged skill artifact in the workspace beyond ClawHub repository files and scan diagnostics.
Based on the available scan inputs, there is no evidence of malicious or suspicious behavior. Because the actual skill artifact was not visible in the workspace, review the skill's manifest and instructions before installing if you need assurance about what files, tools, or credentials it can access.
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.