Shell command execution detected (child_process).
Critical
- Code
- suspicious.dangerous_exec
- Location
- test-skill.js:22
Security audit
Agent Config Validator
Security checks across malware telemetry and agentic risk
Overview
This is a local OpenClaw configuration validator whose file access and optional repairs match its stated purpose, with care needed when using fix mode or the test wrapper.
Install only if you want a local OpenClaw config validator. Start with read-only or --dry-run mode, review reports before sharing them, and use --fix only in a trusted workspace after confirming backups. Avoid running test-skill.js with untrusted environment variables or paths.
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
65/65 vendors flagged this skill as clean.
Static analysis
Detected: suspicious.dangerous_exec