Security audit
Trigger Evaluator
Security checks across malware telemetry and agentic risk
Overview
The skill is narrowly described, but its main action runs an unreviewed hard-coded local script that could affect the OpenClaw database outside the packaged artifact.
Install only if you control the referenced OpenClaw workspace and have reviewed stale_missions_engine.sh at the hard-coded path. Use it on backed-up or non-critical data first, and prefer narrower database credentials for inspection.
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
No suspicious patterns detected.