myskill
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill describing OpenClaw exec options, including powerful modes and safety notes, with no hidden code or automatic behavior.
Install only if you want an agent-facing reference for OpenClaw exec configuration. Treat the documented host, approval, background, and elevated modes carefully: keep sandboxing and approvals enabled where possible, and avoid ask=off or full host access unless you intentionally want commands to affect the local system.
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.