Shell command execution detected (child_process).
Critical
- Code
- suspicious.dangerous_exec
- Location
- skill.js:278
Security audit
AOI OpenClaw Security Toolkit (Core)
Security checks across malware telemetry and agentic risk
Overview
This is a local security-scanning CLI whose file reads, Git checks, and optional local reports match its stated purpose, with no evidence of exfiltration or automatic remediation.
Reasonable to install if you want a local repository security checker. Run it only on projects you intend to scan, narrow scope with --paths and --exclude for sensitive workspaces, keep generated reports private, and treat allowlist or exclude patterns from untrusted repositories cautiously because complex patterns may cause slow scans.
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
Detected: suspicious.dangerous_exec