Security audit
Research Queue
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only research queue skill that transparently manages QUESTIONS.md and optional scheduled OpenClaw research runs.
Install is reasonable if you want an agent-managed research queue. Before enabling automated OpenClaw cron runs, review QUESTIONS.md entries carefully, keep allowedTools minimal, and avoid pointing the queue at secrets, credentials, or sensitive config files unless you explicitly intend that 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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.