Security audit
Agent Supervision
Security checks across malware telemetry and agentic risk
Overview
This skill is a transparent helper for scheduling user-directed check-ins on another OpenClaw agent, with no hidden executable code found.
Install this only if you intend to let an agent supervise another OpenClaw session. Treat the target sessionKey as sensitive, verify the cron interval and escalation rule before enabling it, and keep the tool allowlist limited to session history and session sending as documented.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.